Source: https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/
Canonical: https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/
Language: en

# Qwen2.5 VL 7B Instruct

[Markdown](https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/index.md) · [JSON](https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/facts.json)

## [Qwen2.5 VL 7B Instruct](https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/)

Qwen2.5-VL-7B-Instruct is a visual-language model for images, documents and video. It produces text and structured findings, including object boxes, points and attributes, and brings temporal event localization and visual-agent capabilities to the 7B edition.

- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/#method-0)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/qwen2-5-vl-7b-instruct/#method-1)

About the model

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

Qwen2.5-VL-7B-Instruct is the instruction-tuned 7B edition of Qwen2.5-VL. It connects a text instruction with images or video and returns a text result. The maker's key improvements cover recognition of objects and visual detail, analysis of text and layouts, visual-agent tasks, long-video event understanding, object localization and structured extraction from documents.

Understanding visual content

The family goes beyond identifying the main subject of a photograph. Its documented tasks include analyzing text, charts, icons, graphics and the arrangement of elements inside an image. For a chart, specify the series or relationship to examine and preserve the axes, legend and units. For a diagram, ask how the labeled components connect and what the visible arrangement says about the process.

A useful comparison can supply an original design and a revised design, identify which is which and ask for visible changes against a short list of requirements. Request the observation and the relevant image region together. This gives the answer a concrete purpose instead of asking for a general description of two unrelated pictures.

Visual-agent workflows

The maker positions Qwen2.5-VL as a visual agent that can reason about a screen and direct tools in computer or phone-use tasks. The model provides an interpretation and a proposed operation; a surrounding agent application supplies the controls, executes the operation and returns the new state. A text answer or a predicted coordinate is therefore one part of that integrated workflow.

For an interface question, provide the screenshot and the actual goal, then ask which visible control is relevant and what should be done next. Keep the requested output specific: the control label, its location and the intended action. If the application then performs that action, the next screenshot provides the updated visual input for a subsequent decision.

Long videos and event localization

The maker describes understanding videos longer than one hour and identifying the segment containing a requested event. This extends video description into temporal localization. A task can ask when an object first appears, where a demonstration reaches a particular step or which visible event occurs before another. State whether the result should be a summary, an ordered event list or start and end times with an event description.

The family trains with dynamic frame-rate sampling and aligns temporal positional information with absolute time. Frame-rate information therefore belongs to video preparation, rather than being an arbitrary label that can be discarded when timestamps matter. The documented long-video ability is not a universal file-size or maximum-duration specification for every input path.

Object localization and structured documents

Qwen2.5-VL can return bounding boxes or points and organize coordinates and attributes as JSON. The release uses coordinates on the actual image-size scale instead of traditional normalized coordinates. Specify whether the task needs an enclosing box, a particular point or an object description, and retain the image dimensions and any resizing information needed to interpret the returned location.

For example, a visual inventory request can ask for each target object, its box and a visible attribute. A point-based task can ask for the location of a labeled control or a specified part of an object. These are proposed output designs, not fixed field names that every request must use. Keep each coordinate associated with its source image when several images are supplied.

The maker separately highlights structured extraction from invoice scans, forms and tables. Define the fields, preserve the original labels and request an explicit representation when a value cannot be read. For a table, keep column headings and units with the requested rows. A practical record can contain the document identifier, field label, extracted value and location, making the output usable for a later comparison or human inspection.

Architecture and input preparation

The model combines dynamic image resolution and dynamic video sampling with updated multimodal rotary positional information. Its vision encoder uses window attention, SwiGLU and RMSNorm. These are architecture changes supporting visual and temporal processing; they do not add audio input or image generation to the documented text-result workflow.

The card demonstrates a single image, multiple images, a video frame sequence, a video file or reference, and batched conversations. The image processor documents a default range of 4 to 16,384 visual tokens per image. Minimum and maximum pixel settings preserve aspect ratio; requested exact dimensions are rounded to a multiple of 28. The example range of 256 to 1,280 visual tokens is an adjustable illustration, not a separate hard image limit. Retain the detail needed by the question when choosing a resize.

Context and localization-sensitive settings

The released configuration sets maximum positions to 128,000. The model card's long-text section separately describes a 32,768-token baseline and a YaRN extension example. It explicitly warns that this extension significantly affects temporal and spatial localization and does not recommend it. The guide also discusses changing maximum positions for long videos; these are configuration notes rather than one unconditional input limit for every task.

Keep the exact release configuration and visual preprocessing aligned with the task, especially when coordinates or event times matter. The card's 128-token generation example does not specify a separate maximum output capacity. Qwen2.5-VL-7B-Instruct produces text, coordinates and structured findings; an external action, rendered image, video or spoken answer requires another application component.

Practical task

### Extract a transcribed invoice table

Technical example in English

```
Extract a transcribed invoice table

Extract line items from this invoice transcription: "Invoice N-33; item | quantity | unit price; Clip | 4 | 2.50; Folder | 2 | unreadable." Return each item with quantity, unit price and source invoice ID. Mark the unreadable price explicitly and do not infer it from a total. No image is supplied.
```

#### Expected result

```
A two-row field table retaining N-33 and an explicit unreadable value for the folder unit price.
```

#### Check the result

```
Verify quantities are not swapped and the unreadable price is neither zero nor a guessed amount.
```

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `qwen2.5-vl-7b-instruct`

[`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=chat)

Alibaba /`qwen2.5-vl-7b-instruct`

### Overview

Qwen2.5-VL-7B-Instruct is a visual-language model for images, documents and video. It produces text and structured findings, including object boxes, points and attributes, and brings temporal event localization and visual-agent capabilities to the 7B edition.

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 qwen2.5-vl-7b-instruct | 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

Not specified When fast mode is selected

Flex mode

Not specified When flex mode is selected

Maximum reasoning effort

Not specified When maximum reasoning effort uses the default adjustment

#### Ailoot rates

#### Prices by configuration

| Configuration | Rate schedule | Charge |
| --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0.0001** / 1K tokens Output · Output tokens **$0.0001** / 1K tokens Input · Cache read **$0** / 1K tokens Input · Cache write **$0** / 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": "qwen2.5-vl-7b-instruct", "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='qwen2.5-vl-7b-instruct',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='qwen2.5-vl-7b-instruct',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

**Ailoot Ultra** [`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=chat)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `qwen2.5-vl-7b-instruct`

[`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=messages)

Alibaba /`qwen2.5-vl-7b-instruct`

### Overview

Qwen2.5-VL-7B-Instruct is a visual-language model for images, documents and video. It produces text and structured findings, including object boxes, points and attributes, and brings temporal event localization and visual-agent capabilities to the 7B edition.

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 qwen2.5-vl-7b-instruct | 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

Not specified When fast mode is selected

Flex mode

Not specified When flex mode is selected

Maximum reasoning effort

Not specified When maximum reasoning effort uses the default adjustment

#### Ailoot rates

#### Prices by configuration

| Configuration | Rate schedule | Charge |
| --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens **$0.0001** / 1K tokens Output · Output tokens **$0.0001** / 1K tokens Input · Cache read **$0** / 1K tokens Input · Cache write **$0** / 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": "qwen2.5-vl-7b-instruct",
  "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': 'qwen2.5-vl-7b-instruct', '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': 'qwen2.5-vl-7b-instruct', '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

**Ailoot Ultra** [`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=messages)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`qwen2.5-vl-7b-instruct`](https://ailoot.ai/models/en/#m=qwen2.5-vl-7b-instruct&route=Ultra&caller=qwen2.5-vl-7b-instruct&fmt=messages)

FAQ · Pro/Qwen/Qwen2.5-VL-7B-Instruct

What inputs and results are available?

`POST /v1/chat/completions` · `qwen2.5-vl-7b-instruct`: `text` → `text` `POST /v1/messages` · `qwen2.5-vl-7b-instruct`: `text` → `json`, `sse`

Which fields does the request use?

`POST /v1/chat/completions` · `qwen2.5-vl-7b-instruct`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `qwen2.5-vl-7b-instruct`: `model`, `messages`, `max_tokens`, `stream`

What limits apply?

`POST /v1/chat/completions` · `qwen2.5-vl-7b-instruct`: `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.