Source: https://ailoot.ai/models/en/z-ai-glm-5-3-flash/
Canonical: https://ailoot.ai/models/en/z-ai-glm-5-3-flash/
Language: en

# Z.ai: GLM 5.3 Flash

[Markdown](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/index.md) · [JSON](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/facts.json)

## [Z.ai: GLM 5.3 Flash](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/)

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-0)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-1)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-2)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-3)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-4)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.5`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-5)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.5`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-6)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.5`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-7)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.5-air`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-8)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.5-air`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-9)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.5-air`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-10)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.6`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-11)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.6`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-12)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.6`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-13)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.7`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-14)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.7`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-15)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.7`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-16)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-5-turbo`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-17)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-5-turbo`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-18)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-5-turbo`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-19)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-20)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-21)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-22)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-flash-latest`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-23)
- [**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-flash-latest`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-24)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-flash-latest`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-25)
- [**Ailoot · Anthropic Messages** `POST /v1/messages` `z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-26)
- [**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-27)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-28)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-29)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-30)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/z-ai-glm-5-3-flash/#method-31)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

#### A multimodal model for work

GLM 5.3 Flash combines understanding of text, images, video and files. It produces a text response and is intended for coding with visual feedback, document processing and professional tasks. Context of up to one million tokens and maximum output of 128 thousand tokens are declared.

#### Long-context architecture

The model contains 320 billion parameters, with 18 billion active. Hybrid attention combines sparse and linear processing, while specialized inter-layer connections help maintain stability as scale increases. Multimodal material is included in pretraining.

Visual information participates in the workflow: an assistant examines an interface or rendered result, compares it with the task and proposes corrections. This explains the manufacturer's emphasis on checking the actual visual result after writing code.

#### Reasoning, tools and data

Reasoning is always enabled. Depth is selected through `low`, `high` and `max`; a disabled mode is not provided. Reasoning history can be retained between steps during long workflows.

For a tool, the model produces a function name and arguments, the application executes the action and passes the result back. JSON is suitable for programmatic response processing: expected fields are specified through instructions, while syntax and value meaning are checked separately. Streaming allows text to be received incrementally.

Caching a repeated instruction or history helps reuse processed context. According to Z.ai, it reduces repeated processing in suitable tasks; actual reuse is determined by the result of the particular request.

#### Development from a visual prompt

The model can analyze multiple screenshots of one product, relationships between pages, shared components, interface states and animations. In an agentic environment with tools, it writes code, runs an application, inspects screenshots of the result and corrects mismatches. In game development, this cycle covers rules, movement, interactions, scores and ending a game session.

#### Documents and professional analysis

For presentations, reports and spreadsheets, the model considers content together with layout: text, images, diagrams and element placement. Through tools, it can create and check PPTX, PDF, DOCX and XLSX material. These files are application results; the model's direct response remains text.

Financial analysis includes work with reporting, checks of formula consistency and separate consideration of disclosed data, assumptions and conclusions. In the manufacturer's described workflow, data comes from the task material.

#### Video, three-dimensional scenes and interfaces

In an agentic environment, the model can analyze video, the temporal sequence of events, participants' visual characteristics and subtitles. Tools provide editing and saving of the result.

When working with a three-dimensional scene or drawing, it connects spatial descriptions, proportions and visible results. The tool cycle includes construction, rendering from a specified viewpoint, visual comparison and correction. Similarly, the model can analyze an application screen and help with sequential interface work.

These workflows describe model properties in an environment with the necessary tools. Accepted material is determined by the selected method; visual understanding does not mean that video or file processing, or creation of the listed artifacts, is automatically available in every request.

Practical task

### Audit a report calculation

Technical example in English

```
Audit a report calculation

Review these report rows supplied as text: revenue 12,000; cost of goods 7,000; delivery expense 800; reported gross profit 4,200. The report defines gross profit as revenue minus cost of goods, excluding delivery. Identify the formula mismatch, show the defined calculation and suggest a separate label for the delivery-adjusted figure.
```

#### Expected result

```
A formula check, arithmetic using the given definition and a suggested label distinguishing the two measures.
```

#### Check the result

```
Check that the report's stated definition, rather than an invented accounting rule, determines the correction.
```

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-5.3-flash`

[`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages)

Z.ai /`glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-5.3-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-5.3-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-5.3-flash',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-5.3-flash`

[`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses)

Z.ai /`glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5.3-flash | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-5.3-flash", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-5.3-flash", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-5.3-flash", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-5.3-flash`

[`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat)

Z.ai /`glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5.3-flash", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-5.3-flash",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-5.3-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `glm-5.3-flash`

[`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

Z.ai /`glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Model-specific | Default— |
| Field`messages[].content` | Type`string` | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages |
| Parameter`material_types` | Contracttext |
| Parameter`messages` | Contractmessage array with role/content shape |
| Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
| Parameter`optional_controls` | Contractstream |
| Parameter`control_scope` | ContractText conversation; stream is a boolean and defaults to false. |
| Parameter`output_modalities` | Contracttext |
| Parameter`hosted_operations` | Contractfalse |
| Parameter`multimodal_input_binding` | Contractnull |

Method aliases: `/chat/completions`

Lifecycle: `synchronous_or_streamed`

Send exact model ID with messages.

Context length is not an output cap.

A text file may supply literal text; image/audio/file-object inputs need exact binding.

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · OpenAI Chat

curlPython SDK

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model":"glm-5.3-flash","messages":[{"role":"user","content":"hello"}],"stream":false}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model="glm-5.3-flash", messages=[{"role":"user","content":"hello"}], stream=False)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
```

### Receive and save results

#### Ailoot Ultra · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `glm-5.3-flash`

[`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

Z.ai /`glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

json · sse

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`json`, `sse`

Output format

JSON or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |

Input material combinations

**Text** · UTF-8 text

`messages[].content string`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractstream |
| Parameter`material_types` | Contracttext |
| Parameter`text_file_material` | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |

Lifecycle: `synchronous_or_streamed`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result

```json
{
  "model": "glm-5.3-flash",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```

```python
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```

### Receive and save results

#### Ailoot Ultra · Anthropic Messages

JSON or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.5`

[`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages)

Z.ai /`glm-4.5`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-4.5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-4.5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-4.5',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.5`

[`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses)

Z.ai /`glm-4.5`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5 | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-4.5", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-4.5", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-4.5", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.5`

[`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat)

Z.ai /`glm-4.5`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-4.5",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-4.5",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-4.5',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.5-air`

[`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages)

Z.ai /`glm-4.5-air`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5-air | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-4.5-air",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-4.5-air",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-4.5-air',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.5-air`

[`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses)

Z.ai /`glm-4.5-air`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5-air | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-4.5-air", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-4.5-air", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-4.5-air", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.5-air`

[`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat)

Z.ai /`glm-4.5-air`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.5-air | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.5-air", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-4.5-air",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-4.5-air",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-4.5-air',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.6`

[`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages)

Z.ai /`glm-4.6`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.6 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-4.6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-4.6",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-4.6',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.6`

[`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses)

Z.ai /`glm-4.6`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.6 | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-4.6", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-4.6", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-4.6", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.6`

[`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat)

Z.ai /`glm-4.6`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.6 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.6", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-4.6",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-4.6",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-4.6',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-4.7`

[`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages)

Z.ai /`glm-4.7`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.7 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text examplePython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.7", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-4.7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-4.7",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-4.7',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-4.7`

[`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses)

Z.ai /`glm-4.7`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.7 | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text examplePython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.7", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-4.7", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-4.7", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-4.7", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-4.7`

[`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat)

Z.ai /`glm-4.7`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-4.7 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text examplePython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-4.7", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-4.7",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-4.7",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-4.7',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-5-turbo`

[`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages)

Z.ai /`glm-5-turbo`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5-turbo | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-5-turbo",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-5-turbo",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-5-turbo',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-5-turbo`

[`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses)

Z.ai /`glm-5-turbo`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5-turbo | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-5-turbo", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-5-turbo", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-5-turbo", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-5-turbo`

[`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat)

Z.ai /`glm-5-turbo`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-5-turbo | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-5-turbo", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-5-turbo",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-5-turbo",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-5-turbo',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-flash`

[`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages)

Z.ai /`glm-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-flash',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-flash`

[`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses)

Z.ai /`glm-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-flash", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-flash", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-flash", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-flash`

[`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat)

Z.ai /`glm-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-flash",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-flash",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `glm-flash-latest`

[`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages)

Z.ai /`glm-flash-latest`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash-latest | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

**Text + image**

`{type:image,source:{type:base64,media_type,data}} or source type=url`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="glm-flash-latest",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "glm-flash-latest",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='glm-flash-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Responses** `POST /v1/responses` `glm-flash-latest`

[`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses)

Z.ai /`glm-flash-latest`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Responses** `POST /v1/responses`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash-latest | Default— |
| Field`input` | Type`string\|input_item[]` | RequirementRequired | Values & limits | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`input[].type` | Type`string` | RequirementOptional | Values & limits message, reasoning, function\_call, function\_call\_output | Default— |
| Field`input[].content` | Type`string\|content_part[]` | RequirementOptional | Values & limits | Default— |
| Field`input[].call_id` | Type`string` | RequirementOptional | Values & limits Applies when: function\_call\_output; retain actual returned call\_id | Default— |
| Field`input[].output` | Type`string\|content_part[]` | RequirementOptional | Values & limits Applies when: function\_call\_output | Default— |
| Field`max_output_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning.summary` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`text.verbosity` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`include` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`store` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`previous_response_id` | Type`string` | RequirementOptional | Values & limits ID requirement: Only an actual response ID from a supported continuation Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_key` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`input text or input_text part`

**Text + image**

`{type:input_image,image_url}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, input |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Responses

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="glm-flash-latest", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "glm-flash-latest", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="glm-flash-latest", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Responses

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every output item and content part, actual function call\_id, encrypted reasoning and usage. In streaming retain complete event/item identity.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`status` | Typestring |
| Field`output[]` | Typemessage\|reasoning\|function\_call\|other item |
| Field`output[].content[]` | Typecontent part |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=responses), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=responses), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=responses), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=responses), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=responses), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=responses), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=responses), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=responses), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `glm-flash-latest`

[`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat)

Z.ai /`glm-flash-latest`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text · Images

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`, `image`

Output types

`text`

Context

1,000,000 tokens

Maximum output

131,072 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits glm-flash-latest | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

**Text + image**

`{type:image_url,image_url:{url,detail}}`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext, image |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text exampleImage inputPython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "glm-flash-latest", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="image/png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "image/jpeg" if raw.startswith(b"\xff\xd8") else "image/webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else None
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="glm-flash-latest",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "glm-flash-latest",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='glm-flash-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot · Anthropic Messages** `POST /v1/messages` `z-ai/glm-5.3-flash`

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)

Z.ai /`z-ai/glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`text`

Context

1,048,576 tokens

Maximum output

32,768 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits z-ai/glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string\|content_block[]` | RequirementRequired | Values & limits | Default— |
| Field`system` | Type`string\|content_block[]` | RequirementOptional | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits Minimum: 1 Limit applies to: exact selected model/card ceiling | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop_sequences` | Type`string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].name` | Type`string` | RequirementOptional | Values & limits Applies when: tool supplied | Default— |
| Field`tools[].description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].input_schema` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`thinking.budget_tokens` | Type`integer` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`output_config.effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`metadata` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`cache_control` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content or type=text block`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Cache write

$0.00015 */ 1K*

Cache write, 5 min

$0.00015 */ 1K tokens*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · Anthropic Messages

Text examplePython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "z-ai/glm-5.3-flash", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="z-ai/glm-5.3-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))
```

```js
import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "z-ai/glm-5.3-flash",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);
```

```python
import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='z-ai/glm-5.3-flash',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · Anthropic Messages

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot · OpenAI Chat** `POST /v1/chat/completions` `z-ai/glm-5.3-flash`

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)

Z.ai /`z-ai/glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `glm-4.5`
- `glm-4.5-air`
- `glm-4.6`
- `glm-4.7`
- `glm-5-turbo`
- `glm-flash`
- `glm-flash-latest`
- `z-ai/glm-5.3-flash`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Context

4,096 tokens

Maximum output

1,024 tokens

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits z-ai/glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`material_types` | Contracttext |
| Parameter`required` | Contractmodel, messages |
| Parameter`optional_controls` | Contractnull |
| Parameter`content_type` | Contractapplication/json |
| Parameter`text_file_material` | Contractactual UTF-8 content inserted as text; file IDs/URLs need separate exact support |

Lifecycle: `exact retained published method`

Method shapes and IDs are exact; supplier capability is separate from admission.

### Pricing

#### Ailoot method rates

Input

$0.00015 */ 1K*

Output

$0.0005 */ 1K*

Cache read

≈$0.00003 */ 1K*

Cache write

$0.00015 */ 1K*

Cache write, 5 min

$0.00015 */ 1K tokens*

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Model reference schedules

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationOpenAI Chat · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationOpenAI Chat · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Base token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationAnthropic Messages · Request-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

### Example requests

#### Ailoot · OpenAI Chat

Text examplePython SDKNode.js SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "z-ai/glm-5.3-flash", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="z-ai/glm-5.3-flash",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))
```

```js
import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "z-ai/glm-5.3-flash",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? "png" : raw[0]===255 && raw[1]===216 ? "jpg" : raw.subarray(0,4).toString()==="RIFF" && raw.subarray(8,12).toString()==="WEBP" ? "webp" : suffix;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `z-ai/glm-5.3-flash`

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat)

Z.ai /`z-ai/glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits z-ai/glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits function Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`modalities` | Type`string[]` | RequirementOptional | Values & limits text | Default— |
| Field`provider` | Type`object` | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
| Field`cache_control.ttl` | Type`string` | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages |
| Parameter`material_types` | Contracttext |
| Parameter`messages` | Contractmessage array with role/content shape |
| Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
| Parameter`optional_controls` | Contractstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Contractmodel-specific; user function tools differ from hosted tools |
| Parameter`output_modalities` | Contracttext |
| Parameter`hosted_operations` | Contractfalse |
| Parameter`multimodal_input_binding` | Contractnull |

Lifecycle: `synchronous_or_streamed`

Send exact model ID with messages.

Context length is not an output cap.

A text file may supply literal text; image/audio/file-object inputs need exact binding.

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "z-ai/glm-5.3-flash", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='z-ai/glm-5.3-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot Ultra · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `z-ai/glm-5.3-flash`

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages)

Z.ai /`z-ai/glm-5.3-flash`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

json · sse

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`json`, `sse`

Output format

JSON or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits z-ai/glm-5.3-flash | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |

Input material combinations

**Text** · UTF-8 text

`messages[].content string`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractstream |
| Parameter`material_types` | Contracttext |
| Parameter`text_file_material` | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |

Lifecycle: `synchronous_or_streamed`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result

```json
{
  "model": "z-ai/glm-5.3-flash",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```

```python
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```

### Receive and save results

#### Ailoot Ultra · Anthropic Messages

JSON or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `~z-ai/glm-flash-latest`

[`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

Z.ai /`~z-ai/glm-flash-latest`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits ~z-ai/glm-flash-latest | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits function Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`modalities` | Type`string[]` | RequirementOptional | Values & limits text | Default— |
| Field`provider` | Type`object` | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
| Field`cache_control.ttl` | Type`string` | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages |
| Parameter`material_types` | Contracttext |
| Parameter`messages` | Contractmessage array with role/content shape |
| Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
| Parameter`optional_controls` | Contractstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Contractmodel-specific; user function tools differ from hosted tools |
| Parameter`output_modalities` | Contracttext |
| Parameter`hosted_operations` | Contractfalse |
| Parameter`multimodal_input_binding` | Contractnull |

Lifecycle: `synchronous_or_streamed`

Send exact model ID with messages.

Context length is not an output cap.

A text file may supply literal text; image/audio/file-object inputs need exact binding.

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "~z-ai/glm-flash-latest", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='~z-ai/glm-flash-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='~z-ai/glm-flash-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot Ultra · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=chat), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=chat), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=chat), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=chat), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=chat), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=chat), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=chat), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=chat), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=chat), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `~z-ai/glm-flash-latest`

[`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

Z.ai /`~z-ai/glm-flash-latest`

Model ID

- `glm-5.3-flash`
- `z-ai/glm-5.3-flash`
- `~z-ai/glm-flash-latest`

### Overview

GLM 5.3 Flash is a Z.ai multimodal model for visual development, document analysis and agentic work with text results.

Accepted inputs

Text

Results

json · sse

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`json`, `sse`

Output format

JSON or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits ~z-ai/glm-flash-latest | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |

Input material combinations

**Text** · UTF-8 text

`messages[].content string`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractstream |
| Parameter`material_types` | Contracttext |
| Parameter`text_file_material` | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |

Lifecycle: `synchronous_or_streamed`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · max

Standard rate When reasoning effort is max

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.0003** / 1K tokens Output · Output tokens **$0.001** / 1K tokens Input · Cache read **$0.00006** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result

```json
{
  "model": "~z-ai/glm-flash-latest",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```

```python
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```

### Receive and save results

#### Ailoot Ultra · Anthropic Messages

JSON or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

<strong>Ailoot</strong> [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages)
**Ailoot Ultra** [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages)

#### Method path aliases

`/chat/completions`

#### Related caller IDs

[`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`z-ai/glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=z-ai%2Fglm-5.3-flash&fmt=messages), [`glm-4.5`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5&fmt=messages), [`glm-4.5-air`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.5-air&fmt=messages), [`glm-4.6`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.6&fmt=messages), [`glm-4.7`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-4.7&fmt=messages), [`glm-5-turbo`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5-turbo&fmt=messages), [`glm-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash&fmt=messages), [`glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-flash-latest&fmt=messages), [`~z-ai/glm-flash-latest`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=~z-ai%2Fglm-flash-latest&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Core&caller=glm-5.3-flash&fmt=messages), [`glm-5.3-flash`](https://ailoot.ai/models/en/#m=z-ai%2Fglm-5.3-flash&route=Ultra&caller=glm-5.3-flash&fmt=messages)

FAQ · z-ai/glm-5.3-flash

What inputs and results are available?

`POST /v1/messages` · `glm-5.3-flash`: `text`, `image` → `text` `POST /v1/responses` · `glm-5.3-flash`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-5.3-flash`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-5.3-flash`: `text` → `text` `POST /v1/messages` · `glm-5.3-flash`: `text` → `json`, `sse` `POST /v1/messages` · `glm-4.5`: `text`, `image` → `text` `POST /v1/responses` · `glm-4.5`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-4.5`: `text`, `image` → `text` `POST /v1/messages` · `glm-4.5-air`: `text`, `image` → `text` `POST /v1/responses` · `glm-4.5-air`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-4.5-air`: `text`, `image` → `text` `POST /v1/messages` · `glm-4.6`: `text`, `image` → `text` `POST /v1/responses` · `glm-4.6`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-4.6`: `text`, `image` → `text` `POST /v1/messages` · `glm-4.7`: `text` → `text` `POST /v1/responses` · `glm-4.7`: `text` → `text` `POST /v1/chat/completions` · `glm-4.7`: `text` → `text` `POST /v1/messages` · `glm-5-turbo`: `text`, `image` → `text` `POST /v1/responses` · `glm-5-turbo`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-5-turbo`: `text`, `image` → `text` `POST /v1/messages` · `glm-flash`: `text`, `image` → `text` `POST /v1/responses` · `glm-flash`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-flash`: `text`, `image` → `text` `POST /v1/messages` · `glm-flash-latest`: `text`, `image` → `text` `POST /v1/responses` · `glm-flash-latest`: `text`, `image` → `text` `POST /v1/chat/completions` · `glm-flash-latest`: `text`, `image` → `text` `POST /v1/messages` · `z-ai/glm-5.3-flash`: `text` → `text` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `text` → `text` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `text` → `text` `POST /v1/messages` · `z-ai/glm-5.3-flash`: `text` → `json`, `sse` `POST /v1/chat/completions` · `~z-ai/glm-flash-latest`: `text` → `text` `POST /v1/messages` · `~z-ai/glm-flash-latest`: `text` → `json`, `sse`

Which fields does the request use?

`POST /v1/messages` · `glm-5.3-flash`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-5.3-flash`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-5.3-flash`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `glm-5.3-flash`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-5.3-flash`: `model`, `messages`, `max_tokens`, `stream` `POST /v1/messages` · `glm-4.5`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-4.5`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-4.5`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-4.5-air`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-4.5-air`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-4.5-air`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-4.6`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-4.6`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-4.6`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-4.7`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-4.7`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-4.7`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-5-turbo`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-5-turbo`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-5-turbo`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-flash`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-flash`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-flash`: `model`, `messages`, `stream` `POST /v1/messages` · `glm-flash-latest`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/responses` · `glm-flash-latest`: `model`, `input`, `instructions`, `stream` `POST /v1/chat/completions` · `glm-flash-latest`: `model`, `messages`, `stream` `POST /v1/messages` · `z-ai/glm-5.3-flash`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `model`, `messages`, `stream` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `z-ai/glm-5.3-flash`: `model`, `messages`, `max_tokens`, `stream` `POST /v1/chat/completions` · `~z-ai/glm-flash-latest`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `~z-ai/glm-flash-latest`: `model`, `messages`, `max_tokens`, `stream`

What limits apply?

`POST /v1/messages` · `glm-5.3-flash`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-5.3-flash`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-5.3-flash`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/chat/completions` · `glm-5.3-flash`: `messages.min_items`: `1` `POST /v1/messages` · `glm-4.5`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-4.5`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-4.5`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-4.5-air`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-4.5-air`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-4.5-air`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-4.6`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-4.6`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-4.6`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-4.7`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-4.7`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-4.7`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-5-turbo`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-5-turbo`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-5-turbo`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-flash`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-flash`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-flash`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `glm-flash-latest`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/responses` · `glm-flash-latest`: `ctx`: `1000000`; `max_out`: `131072` `POST /v1/chat/completions` · `glm-flash-latest`: `ctx`: `1000000`; `max_out`: `131072`; `messages.min_items`: `1` `POST /v1/messages` · `z-ai/glm-5.3-flash`: `ctx`: `1048576`; `max_out`: `32768`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `ctx`: `4096`; `max_out`: `1024`; `messages.min_items`: `1` `POST /v1/chat/completions` · `z-ai/glm-5.3-flash`: `messages.min_items`: `1` `POST /v1/chat/completions` · `~z-ai/glm-flash-latest`: `messages.min_items`: `1`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.