Source: https://ailoot.ai/models/ms/gemini-2-5-flash-lite/
Canonical: https://ailoot.ai/models/ms/gemini-2-5-flash-lite/
Language: ms

# Google: Gemini 2.5 Flash Lite

[Markdown](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/index.md) · [JSON](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/facts.json)

## [Google: Gemini 2.5 Flash Lite](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/)

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

- [**Ailoot · Anthropic Messages** `POST /v1/messages` `gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-0)
- [**Ailoot · Gemini generateContent** `POST /v1beta/models/{model}:generateContent` `gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-1)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-2)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-3)
- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-4)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/gemini-2-5-flash-lite/#method-5)

Tentang model

Huraian ini merangkumi keupayaan model. Input, output dan pilihan yang tersedia di Ailoot disenaraikan di bawah untuk kaedah yang dipilih.

Gemini 2.5 Flash-Lite ialah profil ringan stabil Google untuk terjemahan berjumlah tinggi, pengelasan dan pengekstrakan data mudah. Penaakulan hibridnya boleh menggunakan atau meninggalkan pemikiran mengikut tugas. Ia menerima teks, imej, audio, video dan PDF serta menghasilkan teks. Hasil berguna ialah kategori, terjemahan padat, rekod diekstrak daripada bahan dibekalkan atau penerangan bertulis terbatas.

Untuk pengelasan, tetapkan kategori, peraturan keputusan dan bentuk jawapan. Kekalkan pengecam sumber dalam hasil apabila beberapa item bebas diproses. Untuk pengelasan mesej sokongan, kelaskan mesej sokongan mengikut jenis isu dan kembalikan ayat yang menyokong kategori. Sertakan peraturan bagi bukti tiada atau kabur supaya jawapan lancar tidak mengisi medan wajib dengan tekaan. Peranan ringan model paling berguna apabila input dan hasil wajib ditetapkan dengan jelas.

Pemikiran dinyahaktifkan secara lalai dalam konfigurasi 2.5 Flash-Lite yang didokumenkan. Panduan pemikiran GenerateContent Google membenarkan belanjawan pemikiran jelas daripada 512 hingga 24,576 token, sifar untuk mengekalkan pemikiran nyahaktif dan -1 untuk meminta pemikiran dinamik. Itu ialah kawalan belanjawan penaakulan, berasingan daripada peruntukan respons akhir. Aktifkan penaakulan tambahan apabila pengekstrakan mempunyai syarat yang saling berinteraksi atau pengelasan mempunyai pengecualian; penukaran terus boleh mengekalkan tingkah laku tanpa pemikiran lalai. Panduan menyatakan model mungkin menggunakan lebih banyak atau lebih sedikit token pemikiran daripada belanjawan diminta.

Untuk terjemahan, berikan bahasa sasaran, khalayak dan istilah yang perlu dikekalkan. Tetapkan sama ada hasil hanya perlu mengandungi terjemahan atau rekod berlabel. Untuk pengekstrakan dokumen, takrifkan medan dan minta petikan sumber yang membolehkan output disemak. Untuk rakaman, bezakan transkrip daripada ringkasan dan kenal pasti petikan yang penting. Imej atau video boleh menyumbang bukti bagi jawapan teks. Artifak yang diingini perlu kekal jelas walaupun input menggabungkan beberapa jenis media.

Jadual stabil khusus menyenaraikan pemanggilan fungsi, pelaksanaan kod, carian fail, pembumian carian, pembumian Maps, konteks URL dan output berstruktur. Fungsi memerlukan tujuan jelas dan parameter ditetapkan; aplikasi disambungkan melaksanakan operasi dan membekalkan hasil. Untuk pengekstrakan berasaskan skema, sahkan struktur dikembalikan dan bandingkan nilainya dengan bahan asal. Keputusan alat atau rekod terbentuk baik hanya berguna dalam konteks sumber serta bukti sebenar yang dikembalikan.

Kad asal memberikan tetingkap konteks 1M dan output teks 64K. Halaman model API menetapkan 1,048,576 token input dan 65,536 token output. Arahan, kandungan sumber dan perbualan dikekalkan menggunakan belanjawan input, manakala penaakulan serta had respons mempengaruhi sama ada hasil akhir muat. Pemprosesan cache, kelompok, Flex dan Priority disenaraikan bagi profil pengeluar ini. Untuk tugas berulang, kekalkan takrif kategori atau medan sama dan bawa pengecam melalui hasil supaya semakan kemudian boleh menemui item asal.

Profil stabil ini berasingan daripada varian Preview Jun dan September yang diterangkan di bahagian lain keluarga. Kad asal dikongsi melabel penambahbaikan September Preview, termasuk pematuhan arahan dan keringkasan, khusus untuk pratonton itu; ia tidak sepatutnya dipindahkan secara senyap kepada pengecam stabil. Generasi Flash-Lite kemudian juga menggunakan kawalan pemikiran dan jadual keupayaan berbeza. Kekalkan edisi dan pilih tetapan yang didokumenkan untuknya, daripada menggantikan belanjawan 2.5 dengan sintaks aras pemikiran Gemini 3.

Kad menyenaraikan halusinasi serta batasan pemahaman sebab akibat, deduksi logik kompleks dan penaakulan kontrafaktual, serta memberikan tarikh akhir pengetahuan Januari 2025. Bekalkan bukti semasa atau gunakan aliran kerja pembumian yang didokumenkan apabila fakta lebih baharu penting. Semak makna terjemahan, sokongan sumber bagi medan diekstrak dan transkrip terhadap audio. Hasil kecil berfokus menjadikan semakan praktikal tanpa menganggap jawapan digilap sebagai bukti sumber mengandungi butiran yang didakwa.

Tugas praktikal

### Tugas praktikal

Contoh teknikal dalam bahasa Inggeris

```
Translate a pickup instruction

Translate this pickup instruction into French for a customer: "Collect order AR-62 at reception between 14:00 and 17:00. Bring the pickup code. Do not send the code by email." Keep AR-62 and the time range unchanged. Return only the translation, preserving both the required action and the warning.
```

#### Hasil yang dijangka

```
One French translation with the original order ID and time range, without commentary.
```

#### Semak hasil

```
Check the order ID, both times and the prohibition on emailing the code against the source.
```

**Ailoot · Anthropic Messages** `POST /v1/messages` `gemini-2.5-flash-lite`

[`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages)

Google /`gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks · Imej

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`, `image`

Output

`text`

Konteks

1,048,576 tokens

Output maksimum

65,535 tokens

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had gemini-2.5-flash-lite | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_block[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`system` | Jenis`string\|content_block[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had Minimum: 1 Had terpakai pada: had maksimum tepat bagi model/kad yang dipilih | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop_sequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].name` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: alat dibekalkan | Lalai— |
| Medan`tools[].description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].input_schema` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.type` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`thinking.budget_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`output_config.effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`metadata` | Jenis`object` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`cache_control` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content atau blok type=text`

**Teks + imej**

`{type:image,source:{type:base64,media_type,data}} atau sumber dengan type=url`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext, image |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.0001 */ 1K*

Output

USD 0.0004 */ 1K*

Bacaan cache

USD 0.00001 */ 1K*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · Anthropic Messages

Contoh teksInput, imejPython SDKNode.js SDKPenstriman Python

```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": "gemini-2.5-flash-lite", "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": "gemini-2.5-flash-lite", "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="gemini-2.5-flash-lite",
    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: "gemini-2.5-flash-lite",
  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='gemini-2.5-flash-lite',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")
```

### Terima dan simpan hasil

#### Ailoot · Anthropic Messages

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages)

**Ailoot · Gemini generateContent** `POST /v1beta/models/{model}:generateContent` `gemini-2.5-flash-lite`

[`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=gemini)

Google /`gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks · Imej

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

**Ailoot · Gemini generateContent** `POST /v1beta/models/{model}:generateContent`

Input

`text`, `image`

Output

`text`

Format output

json atau penstriman yang disokong

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`path.model` | Jenis`string` | KeperluanDiperlukan | Nilai & had gemini-2.5-flash-lite | Lalai— |
| Medan`contents` | Jenis`content[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`contents[].role` | Jenis`string` | KeperluanPilihan | Nilai & had user, model | Lalai— |
| Medan`contents[].parts` | Jenis`part[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`systemInstruction` | Jenis`content` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`generationConfig.maxOutputTokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`generationConfig.temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`generationConfig.topP` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`generationConfig.topK` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`generationConfig.stopSequences` | Jenis`string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`generationConfig.thinkingConfig.includeThoughts` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`generationConfig.thinkingConfig.thinkingBudget` | Jenis`integer` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].functionDeclarations` | Jenis`function_declaration[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`toolConfig.functionCallingConfig.mode` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`safetySettings` | Jenis`object[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`sessionId` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`contents[].parts[].text`

**Teks + imej**

`parts[].inlineData={mimeType,data}`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`material_types` | Kontraktext, image |
| Parameter`required` | Kontrakcontents |
| Parameter`optional_controls` | Kontraknull |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`text_file_material` | Kontrakkandungan UTF-8 sebenar dimasukkan sebagai teks; ID fail atau alamat URL (URLs) memerlukan sokongan tepat yang berasingan |

Kitar hayat: `exact retained published method`

Struktur kaedah dan ID adalah tepat; keupayaan pembekal berasingan daripada penerimaan permintaan.

### Pelan harga

#### Kadar kaedah Ailoot

Input

USD 0.0001 */ 1K*

Output

USD 0.0004 */ 1K*

Bacaan cache

USD 0.00001 */ 1K*

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

#### Butiran tarif rujukan

Jadual rujukan peringkat model tidak mengubah pemilihan kaedah, sebut harga atau caj. Caj aktif menggunakan kadar kaedah Ailoot yang dipilih.

Jadual rujukan model

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiOpenAI Chat · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiOpenAI Chat · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Kadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiAnthropic Messages · Tahap 1 berdasarkan panjang permintaan | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

### Contoh permintaan

#### Ailoot · Gemini generateContent

Contoh teksInput, imejPython SDKNode.js SDKPenstriman Python

```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('{"contents": []}')
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["contents"]=[{"role":"user","parts":[{"text":"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/v1beta/models/gemini-2.5-flash-lite:generateContent \
  -H "x-goog-api-key: $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('{"contents": [{"role": "user", "parts": [{"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["contents"][0]["parts"].append({"inlineData":{"mimeType":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/v1beta/models/gemini-2.5-flash-lite:generateContent \
  -H "x-goog-api-key: $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 google import genai
from google.genai import types
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = genai.Client(
    api_key=os.environ["AILOOT_API_KEY"],
    http_options=types.HttpOptions(base_url="https://api.ailoot.ai"),
)
resp = client.models.generate_content(model="gemini-2.5-flash-lite", contents="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_json_dict())
```

```js
import { GoogleGenAI } from "@google/genai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const ai = new GoogleGenAI({ apiKey: process.env.AILOOT_API_KEY, httpOptions: { baseUrl: "https://api.ailoot.ai" } });
const resp = await ai.models.generateContent({ model: "gemini-2.5-flash-lite", contents: "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 google import genai
from google.genai import types
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=genai.Client(api_key=os.environ["AILOOT_API_KEY"],http_options=types.HttpOptions(base_url="https://api.ailoot.ai"))
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))

count=0
with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
    for chunk in client.models.generate_content_stream(model='gemini-2.5-flash-lite',contents="Explain observations and hypotheses in three sentences."):
        payload=chunk.to_json_dict()
        log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
        save_result(payload,"stream-chunk-"+str(count))
        count+=1
```

### Terima dan simpan hasil

#### Ailoot · Gemini generateContent

json atau penstriman yang disokong

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua calon dan bahagian, termasuk panggilan fungsi, tandatangan pemikiran dan data penggunaan; gabungkan cebisan strim mengikut urutan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`responseId` | Jenisstring |
| Medan`modelVersion` | Jenisstring |
| Medan`candidates[].content.parts[]` | Jenistext\|inlineData\|functionCall\|other part |
| Medan`candidates[].finishReason` | Jenisstring |
| Medan`usageMetadata` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=gemini)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=gemini), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `gemini-2.5-flash-lite`

[`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=chat)

Google /`gemini-2.5-flash-lite`

ID model

- `gemini-2.5-flash-lite`
- `google/gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had gemini-2.5-flash-lite | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Perbualan teks | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`material_types` | Kontraktext |
| Parameter`messages` | Kontraktatasusunan mesej dengan struktur role/content |
| Parameter`file_material` | Kontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`control_scope` | KontrakPerbualan teks; stream ialah nilai boolean dengan false sebagai lalai. |
| Parameter`output_modalities` | Kontraktext |
| Parameter`hosted_operations` | Kontrakfalse |
| Parameter`multimodal_input_binding` | Kontraknull |

Alias kaedah: `/chat/completions`

Kitar hayat: `synchronous_or_streamed`

Hantar ID model yang tepat bersama messages.

Panjang konteks bukan had output.

Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat.

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Harga cache eksplisit

Tidak diaktifkan Apabila cache eksplisit diminta

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### 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":"gemini-2.5-flash-lite","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="gemini-2.5-flash-lite", 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"))
```

### Terima dan simpan hasil

#### Ailoot Ultra · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`choices[].index` | Jenisinteger |
| Medan`choices[].message.content` | Jenisstring\|null |
| Medan`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Medan`choices[].message.reasoning_content` | Jenisstring |
| Medan`choices[].message.reasoning_details` | Jenisobject\|array |
| Medan`choices[].finish_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=chat), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=chat)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=chat), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `gemini-2.5-flash-lite`

[`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages)

Google /`gemini-2.5-flash-lite`

ID model

- `gemini-2.5-flash-lite`
- `google/gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks

Hasil

json · sse

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`json`, `sse`

Format output

JSON atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had gemini-2.5-flash-lite | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |

Gabungan bahan input

**Teks** · Teks UTF-8

`rentetan messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`material_types` | Kontraktext |
| Parameter`text_file_material` | KontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan. |

Kitar hayat: `synchronous_or_streamed`

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Harga cache eksplisit

Tidak diaktifkan Apabila cache eksplisit diminta

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### Ailoot Ultra · Anthropic Messages

Badan JSON minimum yang lengkapcurl · gunakan dokumen UTF-8 andaPython · simpan hasil lengkap

```json
{
  "model": "gemini-2.5-flash-lite",
  "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': 'gemini-2.5-flash-lite', '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': 'gemini-2.5-flash-lite', '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))
```

### Terima dan simpan hasil

#### Ailoot Ultra · Anthropic Messages

JSON atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages)

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `google/gemini-2.5-flash-lite`

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=chat)

Google /`google/gemini-2.5-flash-lite`

ID model

- `gemini-2.5-flash-lite`
- `google/gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks

Hasil

Teks

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`text`

Format output

json atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had google/gemini-2.5-flash-lite | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had Item minimum: 1 | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had Contoh: system, user, assistant, tool, function Syarat: Peranan ini diwakili secara eksplisit oleh jenis keserasian dalam kod sumber; set peranan model yang tepat kekal khusus untuk setiap model. Bergantung pada model | Lalai— |
| Medan`messages[].content` | Jenis`string\|content_part[]\|null` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_calls` | Jenis`tool_call[]` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].tool_call_id` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: role=tool; gunakan ID sebenar yang dipulangkan | Lalai— |
| Medan`messages[].name` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`messages[].reasoning_content` | Jenis`string` | KeperluanPilihan | Nilai & had Terpakai apabila: Hantar semula penaakulan sebenar yang dipulangkan apabila model ini menggunakannya | Lalai— |
| Medan`messages[].reasoning_details` | Jenis`object\|array` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`max_completion_tokens` | Jenis`integer` | KeperluanPilihan | Nilai & had Minimum: 1 Bergantung pada model | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |
| Medan`stream_options.include_usage` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`temperature` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`top_p` | Jenis`number` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`stop` | Jenis`string\|string[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools` | Jenis`function_tool[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`tools[].type` | Jenis`string` | KeperluanPilihan | Nilai & had function Bergantung pada model | Lalai— |
| Medan`tools[].function.name` | Jenis`string` | KeperluanDiperlukan | Nilai & had Terpakai apabila: alat fungsi dibekalkan | Lalai— |
| Medan`tools[].function.description` | Jenis`string` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tools[].function.parameters` | Jenis`JSON_schema` | KeperluanPilihan | Nilai & had | Lalai— |
| Medan`tool_choice` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`parallel_tool_calls` | Jenis`boolean` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`response_format` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning_effort` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`reasoning` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`service_tier` | Jenis`string` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`instructions` | Jenis`string` | KeperluanPilihan | Nilai & had Medan keserasian | Lalai— |
| Medan`functions` | Jenis`function[]` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`function_call` | Jenis`string\|object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`prompt_cache_options` | Jenis`object` | KeperluanPilihan | Nilai & had Bergantung pada model | Lalai— |
| Medan`modalities` | Jenis`string[]` | KeperluanPilihan | Nilai & had text | Lalai— |
| Medan`provider` | Jenis`object` | KeperluanPilihan | Nilai & had Syarat: provider.options ditolak pada laluan teks Ultra ini | Lalai— |
| Medan`cache_control.ttl` | Jenis`string` | KeperluanPilihan | Nilai & had Syarat: 1h ditolak pada lokasi cache prompt yang digunakan | Lalai— |

Gabungan bahan input

**Teks** · Teks UTF8

`messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages |
| Parameter`material_types` | Kontraktext |
| Parameter`messages` | Kontraktatasusunan mesej dengan struktur role/content |
| Parameter`file_material` | Kontrakdokumen UTF-8 sebenar dimasukkan sebagai teks literal; ID fail tidak diandaikan |
| Parameter`optional_controls` | Kontrakstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Kontrakkhusus model; alat fungsi pengguna berbeza daripada alat yang dihoskan |
| Parameter`output_modalities` | Kontraktext |
| Parameter`hosted_operations` | Kontrakfalse |
| Parameter`multimodal_input_binding` | Kontraknull |

Kitar hayat: `synchronous_or_streamed`

Hantar ID model yang tepat bersama messages.

Panjang konteks bukan had output.

Fail teks boleh membekalkan teks literal; input imej/audio/objek fail memerlukan pengikatan tepat.

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Harga cache eksplisit

Tidak diaktifkan Apabila cache eksplisit diminta

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPenstriman Python

```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": "google/gemini-2.5-flash-lite", "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='google/gemini-2.5-flash-lite',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='google/gemini-2.5-flash-lite',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")
```

### Terima dan simpan hasil

#### Ailoot Ultra · OpenAI Chat

json atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan setiap pilihan jawapan bersama kandungan, panggilan alat dan penaakulannya. Dalam SSE, gabungkan delta mengikut indeks pilihan jawapan/alat dan kekalkan sebab penamatan akhir serta data penggunaan.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`choices[].index` | Jenisinteger |
| Medan`choices[].message.content` | Jenisstring\|null |
| Medan`choices[].message.tool_calls` | Jenistool\_call\[\] |
| Medan`choices[].message.reasoning_content` | Jenisstring |
| Medan`choices[].message.reasoning_details` | Jenisobject\|array |
| Medan`choices[].finish_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=chat), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=chat)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=chat), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=chat)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `google/gemini-2.5-flash-lite`

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages)

Google /`google/gemini-2.5-flash-lite`

ID model

- `gemini-2.5-flash-lite`
- `google/gemini-2.5-flash-lite`

### Pengenalan

Gemini 2.5 Flash-Lite ialah model teks multimodal stabil Google untuk pengelasan kerap, terjemahan dan pengekstrakan mudah. Pemikiran dinyahaktifkan secara lalai dan boleh diaktifkan dengan belanjawan penaakulan 512–24,576 token. Ia menerima teks serta media, dengan alat, output berstruktur dan had input 1,048,576 token.

Input yang diterima

Teks

Hasil

json · sse

### Tersedia di Ailoot · input & kaedah

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

Input

`text`

Output

`json`, `sse`

Format output

JSON atau SSE

| Medan | Jenis | Keperluan | Nilai & had | Lalai |
| --- | --- | --- | --- | --- |
| Medan`model` | Jenis`string` | KeperluanDiperlukan | Nilai & had google/gemini-2.5-flash-lite | Lalai— |
| Medan`messages` | Jenis`message[]` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`messages[].role` | Jenis`string` | KeperluanDiperlukan | Nilai & had user, assistant | Lalai— |
| Medan`messages[].content` | Jenis`string` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`max_tokens` | Jenis`integer` | KeperluanDiperlukan | Nilai & had | Lalai— |
| Medan`stream` | Jenis`boolean` | KeperluanPilihan | Nilai & had | Lalaifalse |

Gabungan bahan input

**Teks** · Teks UTF-8

`rentetan messages[].content`

Parameter kaedah dan kitar hayat

| Parameter | Kontrak |
| --- | --- |
| Parameter`content_type` | Kontrakapplication/json |
| Parameter`required` | Kontrakmodel, messages, max\_tokens |
| Parameter`optional_controls` | Kontrakstream |
| Parameter`material_types` | Kontraktext |
| Parameter`text_file_material` | KontrakBaca dokumen UTF-8 sebenar dan letakkan teksnya dalam rentetan input atau kandungan mesej yang ditunjukkan. |

Kitar hayat: `synchronous_or_streamed`

### Pelan harga

Rujukan tarif tidak menambah pilihan permintaan. Parameter yang disokong disenaraikan untuk kaedah yang dipilih.

Mod pantas

Kadar standard Apabila mod pantas dipilih

Mod flex

Kadar standard Apabila mod flex dipilih

Usaha penaakulan maksimum

Kadar standard Apabila usaha penaakulan maksimum menggunakan pelarasan default

Harga cache eksplisit

Tidak diaktifkan Apabila cache eksplisit diminta

#### Kadar Ailoot

#### Harga mengikut konfigurasi

Padankan setiap caj dengan syarat yang dipaparkan. Gunakan satu kadar bagi setiap set konfigurasi alternatif.

| Konfigurasi | Jadual kadar | Token konteks, melebihi | Token konteks, sehingga dan termasuk | Caj |
| --- | --- | --- | --- | --- |
| KonfigurasiKadar asas token | Jadual kadarKadar asas | Token konteks, melebihi— | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |
| KonfigurasiTahap panjang permintaan 1 | Jadual kadar— | Token konteks, melebihi0 | Token konteks, sehingga dan termasukTiada had atas | Caj Input · Token input **$0.0002** / 1K token Output · Token output **$0.0008** / 1K token Input · Bacaan cache **$0.00002** / 1K token Input · Penulisan cache **$0.0001666666666666666** / 1K token Input · Penulisan cache, 1 jam **—** / 1K token |

Ailoot merizabkan anggaran amaun sebelum permintaan. Selepas hasil diterima, caj akhir diselesaikan berdasarkan penggunaan terukur. Penyelesaian caj penstriman menggunakan rekod penggunaan akhir. [Cara rizab dan penyelesaian caj berfungsi →](https://ailoot.ai/docs/ms/billing/reserve/)

### Contoh permintaan

#### Ailoot Ultra · Anthropic Messages

Badan JSON minimum yang lengkapcurl · gunakan dokumen UTF-8 andaPython · simpan hasil lengkap

```json
{
  "model": "google/gemini-2.5-flash-lite",
  "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': 'google/gemini-2.5-flash-lite', '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': 'google/gemini-2.5-flash-lite', '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))
```

### Terima dan simpan hasil

#### Ailoot Ultra · Anthropic Messages

JSON atau SSE

##### Simpan semua hasil yang selesai

Simpan setiap respons lengkap, fail dan bahagian kandungan yang dikembalikan.

Kekalkan semua blok kandungan, tandatangan penaakulan dan ID penggunaan alat sebenar. Gabungkan semua delta blok SSE; blok teks pertama bukan keseluruhan output.

##### Jika respons asal perlu disemak

Kekalkan ID permintaan/respons dan pengepala. Tiada URL umum bagi pengambilan tugas teks dibekalkan.

Medan respons

| Medan | Jenis |
| --- | --- |
| Medan`id` | Jenisstring |
| Medan`model` | Jenisstring |
| Medan`content[]` | Jenistext\|thinking\|tool\_use\|other content block |
| Medan`stop_reason` | Jenisstring\|null |
| Medan`usage` | Jenisobject |

Ralat dan langkah seterusnya

| Respons | Syarat | Langkah seterusnya |
| --- | --- | --- |
| Respons400 · `invalid_request_error` | SyaratMedan wajib, perwakilan bahan atau nilai parameter tidak sah | Langkah seterusnyaBetulkan medan yang ditunjukkan sebelum permintaan penciptaan baharu. |

### Alias

#### Alias model

<strong>Ailoot</strong> [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages)
**Ailoot Ultra** [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages), [`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages)

#### Alias laluan kaedah

`/chat/completions`

#### ID pemanggil berkaitan

[`google/gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=google%2Fgemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Core&caller=gemini-2.5-flash-lite&fmt=messages), [`gemini-2.5-flash-lite`](https://ailoot.ai/models/ms/#m=google%2Fgemini-2.5-flash-lite&route=Ultra&caller=gemini-2.5-flash-lite&fmt=messages)

FAQ · Google: Gemini 2.5 Flash Lite

Apakah input dan hasil yang tersedia?

`POST /v1/messages` · `gemini-2.5-flash-lite`: `text`, `image` → `text` `POST /v1beta/models/{model}:generateContent` · `gemini-2.5-flash-lite`: `text`, `image` → `text` `POST /v1/chat/completions` · `gemini-2.5-flash-lite`: `text` → `text` `POST /v1/messages` · `gemini-2.5-flash-lite`: `text` → `json`, `sse` `POST /v1/chat/completions` · `google/gemini-2.5-flash-lite`: `text` → `text` `POST /v1/messages` · `google/gemini-2.5-flash-lite`: `text` → `json`, `sse`

Apakah medan yang digunakan oleh permintaan?

`POST /v1/messages` · `gemini-2.5-flash-lite`: `model`, `messages`, `system`, `max_tokens`, `stream`, `metadata` `POST /v1beta/models/{model}:generateContent` · `gemini-2.5-flash-lite`: `contents`, `systemInstruction`, `sessionId` `POST /v1/chat/completions` · `gemini-2.5-flash-lite`: `model`, `messages`, `stream` `POST /v1/messages` · `gemini-2.5-flash-lite`: `model`, `messages`, `max_tokens`, `stream` `POST /v1/chat/completions` · `google/gemini-2.5-flash-lite`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/messages` · `google/gemini-2.5-flash-lite`: `model`, `messages`, `max_tokens`, `stream`

Apakah had yang terpakai?

`POST /v1/messages` · `gemini-2.5-flash-lite`: `ctx`: `1048576`; `max_out`: `65535`; `messages.min_items`: `1`; `max_tokens.minimum`: `1` `POST /v1beta/models/{model}:generateContent` · `gemini-2.5-flash-lite`: `contents.min_items`: `1` `POST /v1/chat/completions` · `gemini-2.5-flash-lite`: `messages.min_items`: `1` `POST /v1/chat/completions` · `google/gemini-2.5-flash-lite`: `messages.min_items`: `1`

Sambungkan Ailoot kepada Claude Code, OpenCode, Hermes atau aplikasi anda.

## Syarikat dan portfolio projeknya

Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.

## Beli token dengan diskaun.

Diskaun langganan untuk penggunaan berkala. Kod promosi — sehingga 50% bagi pembelian token.

Langganan

Pilih pelan berdiskaun untuk permintaan berkala anda.

Kod promosi sehingga 50%

Masukkan kod semasa pembelian. Harga dikira semula mengikut promosi semasa.

Perbelanjaan dalam sejarah

Model, token dan jumlah disimpan bagi setiap permintaan.

[Pilih langganan](https://ailoot.ai/docs/ms/billing/subscriptions/) · [Lihat harga model](https://ailoot.ai/models/ms/)

## Sambungkan API kepada produk yang anda jual.

SaaS, aplikasi dan bot — di bawah tawaran rasmi serta perjanjian lesen Ailoot. Untuk jualan semula, mohon lesen penjual semula.

Aplikasi komersial

Tambahkan penjanaan teks, imej, video dan audio pada ciri berbayar perkhidmatan anda.

Lesen penjual semula

Hantar keterangan projek dan susunan akses. Minta terma penggunaan serta jualan semula secara bertulis.

Dokumen pada laman

Tawaran, perjanjian lesen dan dasar pemprosesan data tersedia sebelum sambungan.

[Mohon lesen penjual semula](mailto:support@ailoot.ai) · [Tawaran dan perjanjian lesen](https://ailoot.ai/legal/offer?lang=ms)

## Ailoot · Syarikat dan portfolio projeknya





Ailoot berteraskan pengalaman operasi yang mantap, pangkalan pelanggan yang besar, perkhidmatan yang stabil dan pemantauan KPI berterusan.





Syarikat dan portfolio projeknya: jutaan pelanggan; jualan bernilai berbilion setiap bulan.





Ailoot menggunakan pengalaman operasi ini untuk akses API kepada ciri AI dalam produk pelanggan, ejen, aplikasi dan automasi.