我們很高興宣布推出 Gemini Embedding 2，這是 Google 首款完全多模態的嵌入模型。

OpenAI 相容性

只要更新三行程式碼並使用 Gemini API 金鑰，即可透過 OpenAI 程式庫 (Python 和 TypeScript/JavaScript) 和 REST API 存取 Gemini 模型。如果您尚未採用 OpenAI 程式庫，建議您直接呼叫 Gemini API。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {   "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

print(response.choices[0].message)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
        {   role: "system",
            content: "You are a helpful assistant." 
        },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

console.log(response.choices[0].message);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

異動內容只要三行！

api_key="GEMINI_API_KEY"：將「GEMINI_API_KEY」替換為實際的 Gemini API 金鑰，您可以在 Google AI Studio 中取得。
base_url="https://generativelanguage.googleapis.com/v1beta/openai/"：這會告知 OpenAI 程式庫將要求傳送至 Gemini API 端點，而非預設網址。
model="gemini-3-flash-preview"：選擇相容的 Gemini 模型

思考中

Gemini 模型經過訓練，能夠思考複雜問題，因此推理能力大幅提升。Gemini API 隨附思考參數，可精細控管模型的思考量。

不同的 Gemini 模型有不同的推理設定，您可以參閱下表，瞭解這些設定如何對應到 OpenAI 的推理工作：

`reasoning_effort` (OpenAI)	`thinking_level` (Gemini 3.1 Pro)	`thinking_level` (Gemini 3.1 Flash-Lite)	`thinking_level` (Gemini 3 Flash)	`thinking_budget` (Gemini 2.5)
`reasoning_effort` (OpenAI)	`thinking_level` (Gemini 3.1 Pro)	`thinking_level` (Gemini 3.1 Flash-Lite)	`thinking_level` (Gemini 3 Flash)	`thinking_budget` (Gemini 2.5)	`minimal`	`low`	`minimal`	`minimal`	`1,024`
`low`	`low`	`low`	`low`	`1,024`
`medium`	`medium`	`medium`	`medium`	`8,192`
`high`	`high`	`high`	`high`	`24,576`

如未指定 reasoning_effort，Gemini 會使用模型的預設層級或預算。

如要停用思考功能，請將 2.5 模型的 reasoning_effort 設為 "none"。Gemini 2.5 Pro 或 3 模型無法關閉推理功能。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    reasoning_effort="low",
    messages=[
        {   "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

print(response.choices[0].message)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    reasoning_effort: "low",
    messages: [
        {   role: "system",
            content: "You are a helpful assistant." 
        },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

console.log(response.choices[0].message);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "reasoning_effort": "low",
    "messages": [
      {
        "role": "user",
        "content": "Explain to me how AI works"
      }
    ]
  }'

Gemini 思考模型也會產生想法摘要。您可以使用 extra_body 欄位，在要求中加入 Gemini 欄位。

請注意，reasoning_effort 和 thinking_level/thinking_budget 的功能重疊，因此無法同時使用。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[{"role": "user", "content": "Explain to me how AI works"}],
    extra_body={
      'extra_body': {
        "google": {
          "thinking_config": {
            "thinking_level": "low",
            "include_thoughts": True
          }
        }
      }
    }
)

print(response.choices[0].message)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [{role: "user", content: "Explain to me how AI works",}],
    extra_body: {
      "google": {
        "thinking_config": {
          "thinking_level": "low",
          "include_thoughts": true
        }
      }
    }
});

console.log(response.choices[0].message);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3-flash-preview",
        "messages": [{"role": "user", "content": "Explain to me how AI works"}],
        "extra_body": {
          "google": {
            "thinking_config": {
              "thinking_level": "low",
              "include_thoughts": true
            }
          }
        }
      }'

Gemini 3 支援 OpenAI 相容性，適用於對話完成 API 中的想法簽章。如需完整範例，請參閱「思想簽章」頁面。

串流

Gemini API 支援串流回應。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=[
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {   "role": "user",
        "content": "Hello!"
    }
  ],
  stream=True
)

for chunk in response:
    print(chunk.choices[0].delta)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
      {
          "role": "system",
          "content": "You are a helpful assistant."
      },
      {
          "role": "user",
          "content": "Hello!"
      }
    ],
    stream: true,
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
      "model": "gemini-3-flash-preview",
      "messages": [
          {"role": "user", "content": "Explain to me how AI works"}
      ],
      "stream": true
    }'

函式呼叫

透過函式呼叫，您可以更輕鬆地從生成模型取得結構化資料輸出內容，且 Gemini API 支援這項功能。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. Chicago, IL",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]

messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(response)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}];
  const tools = [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. Chicago, IL",
              },
              "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
          },
        }
      }
  ];

  const response = await openai.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: messages,
    tools: tools,
    tool_choice: "auto",
  });

  console.log(response);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
  "model": "gemini-3-flash-preview",
  "messages": [
    {
      "role": "user",
      "content": "What'\''s the weather like in Chicago today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. Chicago, IL"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

圖像解讀

Gemini 模型原生支援多模態資料，在許多常見的視覺工作中，都能提供同級最佳效能。

Python

import base64
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Function to encode the image
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

# Getting the base64 string
base64_image = encode_image("Path/to/agi/image.jpeg")

response = client.chat.completions.create(
  model="gemini-3-flash-preview",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url":  f"data:image/jpeg;base64,{base64_image}"
          },
        },
      ],
    }
  ],
)

print(response.choices[0])

JavaScript

import OpenAI from "openai";
import fs from 'fs/promises';

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function encodeImage(imagePath) {
  try {
    const imageBuffer = await fs.readFile(imagePath);
    return imageBuffer.toString('base64');
  } catch (error) {
    console.error("Error encoding image:", error);
    return null;
  }
}

async function main() {
  const imagePath = "Path/to/agi/image.jpeg";
  const base64Image = await encodeImage(imagePath);

  const messages = [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url": `data:image/jpeg;base64,${base64Image}`
          },
        },
      ],
    }
  ];

  try {
    const response = await openai.chat.completions.create({
      model: "gemini-3-flash-preview",
      messages: messages,
    });

    console.log(response.choices[0]);
  } catch (error) {
    console.error("Error calling Gemini API:", error);
  }
}

main();

REST

bash -c '
  base64_image=$(base64 -i "Path/to/agi/image.jpeg");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3-flash-preview\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"What is in this image?\" },
            {
              \"type\": \"image_url\",
              \"image_url\": { \"url\": \"data:image/jpeg;base64,${base64_image}\" }
            }
          ]
        }
      ]
    }"
'

生成圖片

使用 gemini-2.5-flash-image 或 gemini-3-pro-image-preview 生成圖片。支援的參數包括 prompt、model、n、size 和 response_format。相容性層會自動忽略此處或 extra_body 部分未列出的任何其他參數。

您可以使用 extra_body 參數啟用「使用 Google 搜尋進行基本事實檢查」，並設定安全設定。如要瞭解可用的參數，請參閱「extra_body」一節。利用 Google 搜尋建立基準的功能僅適用於 Gemini 3 和後續機型。

Python

import base64
from openai import OpenAI
from PIL import Image
from io import BytesIO

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
)

response = client.images.generate(
    model="gemini-2.5-flash-image",
    prompt="a portrait of a sheepadoodle wearing a cape",
    response_format='b64_json',
    n=1,
)

for image_data in response.data:
  image = Image.open(BytesIO(base64.b64decode(image_data.b64_json)))
  image.show()

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const image = await openai.images.generate(
    {
      model: "gemini-2.5-flash-image",
      prompt: "a portrait of a sheepadoodle wearing a cape",
      response_format: "b64_json",
      n: 1,
    }
  );

  console.log(image.data);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
        "model": "gemini-2.5-flash-image",
        "prompt": "a portrait of a sheepadoodle wearing a cape",
        "response_format": "b64_json",
        "n": 1,
      }'

生成影片

透過與 Sora 相容的veo-3.1-generate-preview/v1/videos端點生成影片。支援的頂層參數為 prompt 和 model。duration_seconds、image 和 aspect_ratio 等其他參數必須與 extra_body 一併傳遞。如要查看所有可用參數，請參閱「extra_body」一節。

影片生成作業是長時間執行的作業，會傳回作業 ID，您可以輪詢作業是否完成。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Returns a Long Running Operation (status: processing)
response = client.videos.create(
    model="veo-3.1-generate-preview",
    prompt="A cinematic drone shot of a waterfall",
)

print(f"Operation ID: {response.id}")
print(f"Status: {response.status}")

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
    // Returns a Long Running Operation (status: processing)
    const response = await openai.videos.create({
        model: "veo-3.1-generate-preview",
        prompt: "A cinematic drone shot of a waterfall",
    });

    console.log(`Operation ID: ${response.id}`);
    console.log(`Status: ${response.status}`);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/videos" \
  -H "Authorization: Bearer $GEMINI_API_KEY" \
  -F "model=veo-3.1-generate-preview" \
  -F "prompt=A cinematic drone shot of a waterfall"

查看影片狀態

影片生成作業為非同步。使用 GET /v1/videos/{id} 輪詢狀態，並在完成時擷取最終影片網址：

Python

import time
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Poll until video is ready
video_id = response.id  # From the create call
while True:
    video = client.videos.retrieve(video_id)
    if video.status == "completed":
        print(f"Video URL: {video.url}")
        break
    elif video.status == "failed":
        print(f"Generation failed: {video.error}")
        break
    print(f"Status: {video.status}. Waiting...")
    time.sleep(10)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
    // Poll until video is ready
    const videoId = response.id;  // From the create call
    while (true) {
        const video = await openai.videos.retrieve(videoId);
        if (video.status === "completed") {
            console.log(`Video URL: ${video.url}`);
            break;
        } else if (video.status === "failed") {
            console.log(`Generation failed: ${video.error}`);
            break;
        }
        console.log(`Status: ${video.status}. Waiting...`);
        await new Promise(resolve => setTimeout(resolve, 10000));
    }
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/videos/VIDEO_ID" \
  -H "Authorization: Bearer $GEMINI_API_KEY"

音訊理解

分析音訊輸入內容：

Python

import base64
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

with open("/path/to/your/audio/file.wav", "rb") as audio_file:
  base64_audio = base64.b64encode(audio_file.read()).decode('utf-8')

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Transcribe this audio",
        },
        {
              "type": "input_audio",
              "input_audio": {
                "data": base64_audio,
                "format": "wav"
          }
        }
      ],
    }
  ],
)

print(response.choices[0].message.content)

JavaScript

import fs from "fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

const audioFile = fs.readFileSync("/path/to/your/audio/file.wav");
const base64Audio = Buffer.from(audioFile).toString("base64");

async function main() {
  const response = await client.chat.completions.create({
    model: "gemini-3-flash-preview",
    messages: [
      {
        role: "user",
        content: [
          {
            type: "text",
            text: "Transcribe this audio",
          },
          {
            type: "input_audio",
            input_audio: {
              data: base64Audio,
              format: "wav",
            },
          },
        ],
      },
    ],
  });

  console.log(response.choices[0].message.content);
}

main();

REST

bash -c '
  base64_audio=$(base64 -i "/path/to/your/audio/file.wav");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-3-flash-preview\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"Transcribe this audio file.\" },
            {
              \"type\": \"input_audio\",
              \"input_audio\": {
                \"data\": \"${base64_audio}\",
                \"format\": \"wav\"
              }
            }
          ]
        }
      ]
    }"
'

結構化輸出內容

Gemini 模型可以輸出您定義的任何結構的 JSON 物件。

Python

from pydantic import BaseModel
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "John and Susan are going to an AI conference on Friday."},
    ],
    response_format=CalendarEvent,
)

print(completion.choices[0].message.parsed)

JavaScript

import OpenAI from "openai";
import { zodResponseFormat } from "openai/helpers/zod";
import { z } from "zod";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai"
});

const CalendarEvent = z.object({
  name: z.string(),
  date: z.string(),
  participants: z.array(z.string()),
});

const completion = await openai.chat.completions.parse({
  model: "gemini-3-flash-preview",
  messages: [
    { role: "system", content: "Extract the event information." },
    { role: "user", content: "John and Susan are going to an AI conference on Friday" },
  ],
  response_format: zodResponseFormat(CalendarEvent, "event"),
});

const event = completion.choices[0].message.parsed;
console.log(event);

嵌入

文字嵌入可衡量字串的關聯性，並使用 Gemini API 生成。您可以使用 gemini-embedding-2-preview 取得多模態嵌入，或使用 gemini-embedding-001 取得純文字嵌入。

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.embeddings.create(
    input="Your text string goes here",
    model="gemini-embedding-2-preview"
)

print(response.data[0].embedding)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const embedding = await openai.embeddings.create({
    model: "gemini-embedding-2-preview",
    input: "Your text string goes here",
  });

  console.log(embedding);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/embeddings" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
    "input": "Your text string goes here",
    "model": "gemini-embedding-2-preview"
  }'

Batch API

您可以使用 OpenAI 程式庫建立批次工作、提交工作，並查看工作狀態。

您需要準備 OpenAI 輸入格式的 JSONL 檔案。例如：

{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3-flash-preview", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3-flash-preview", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}

Batch 的 OpenAI 相容性支援建立批次、監控工作狀態，以及查看批次結果。

目前不支援上傳及下載相容性。不過，下列範例會使用 genai 用戶端上傳及下載檔案，與使用 Gemini Batch API 時相同。

Python

from openai import OpenAI

# Regular genai client for uploads & downloads
from google import genai
client = genai.Client()

openai_client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Upload the JSONL file in OpenAI input format, using regular genai SDK
uploaded_file = client.files.upload(
    file='my-batch-requests.jsonl',
    config=types.UploadFileConfig(display_name='my-batch-requests', mime_type='jsonl')
)

# Create batch
batch = openai_client.batches.create(
    input_file_id=batch_input_file_id,
    endpoint="/v1/chat/completions",
    completion_window="24h"
)

# Wait for batch to finish (up to 24h)
while True:
    batch = client.batches.retrieve(batch.id)
    if batch.status in ('completed', 'failed', 'cancelled', 'expired'):
        break
    print(f"Batch not finished. Current state: {batch.status}. Waiting 30 seconds...")
    time.sleep(30)
print(f"Batch finished: {batch}")

# Download results in OpenAI output format, using regular genai SDK
file_content = genai_client.files.download(file=batch.output_file_id).decode('utf-8')

# See batch_output JSONL in OpenAI output format
for line in file_content.splitlines():
    print(line)

OpenAI SDK 也支援使用 Batch API 生成嵌入內容。如要這麼做，請將 create 方法的 endpoint 欄位換成嵌入端點，並將 JSONL 檔案中的 url 和 model 鍵換成：

# JSONL file using embeddings model and endpoint
# {"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "ggemini-embedding-001", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
# {"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "gemini-embedding-001", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}

# ...

# Create batch step with embeddings endpoint
batch = openai_client.batches.create(
    input_file_id=batch_input_file_id,
    endpoint="/v1/embeddings",
    completion_window="24h"
)

如需完整範例，請參閱 OpenAI 相容性食譜的「批次產生嵌入內容」一節。

使用 `extra_body` 啟用 Gemini 功能

Gemini 支援多項功能，但 OpenAI 模型不支援，不過可以使用 extra_body 欄位啟用。

參數	類型	端點	說明
`cached_content`	文字	即時通訊	對應至 Gemini 的一般內容快取。
`thinking_config`	物件	即時通訊	對應於 Gemini 的 ThinkingConfig。
`aspect_ratio`	文字	圖片	輸出長寬比 (例如 `"16:9"`、`"1:1"`、`"9:16"`)。
`generation_config`	物件	圖片	Gemini 生成設定物件 (例如 `{"responseModalities": ["IMAGE"], "candidateCount": 2}`)。
`safety_settings`	清單	圖片	自訂安全門檻篩選器 (例如 `[{"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}]`)。
`tools`	清單	圖片	啟用依據功能 (例如 `[{"google_search": {}}]`)。僅適用於 `gemini-3-pro-image-preview`。
`aspect_ratio`	文字	影片	輸出影片的尺寸 (橫向為 `16:9`，直向為 `9:16`)。如果未指定，則會從 `size`對應。
`resolution`	文字	影片	輸出解析度 (`720p`、`1080p`、`4K`)。注意：`1080p` 和 `4K` 會觸發升頻管道。
`duration_seconds`	整數	影片	生成長度 (值：`4`、`6`、`8`)。使用 `reference_images`、插補或擴充功能時，必須為 `8`。
`frame_rate`	文字	影片	輸出影片的畫面更新率 (例如 `"24"`)。
`input_reference`	文字	影片	用來生成影片的參考輸入內容。
`extend_video_id`	文字	影片	要延長的現有影片 ID。
`negative_prompt`	文字	影片	要排除的項目 (例如 `"shaky camera"`)。
`seed`	整數	影片	用於決定性生成的整數。
`style`	文字	影片	視覺樣式 (`cinematic` 預設，`creative` 適用於社群媒體)。
`person_generation`	文字	影片	控制人物生成 (`allow_adult`、`allow_all`、`dont_allow`)。
`reference_images`	清單	影片	最多 3 張風格/角色參考圖片 (base64 素材資源)。
`image`	文字	影片	Base64 編碼的初始輸入圖片，用於設定影片生成條件。
`last_frame`	物件	影片	用於插補的最終圖片 (需要 `image` 做為第一個影格)。

使用 `extra_body` 的範例

以下範例說明如何使用 extra_body 設定 cached_content：

Python

from openai import OpenAI

client = OpenAI(
    api_key=MY_API_KEY,
    base_url="https://generativelanguage.googleapis.com/v1beta/"
)

stream = client.chat.completions.create(
    model="gemini-3-flash-preview",
    n=1,
    messages=[
        {
            "role": "user",
            "content": "Summarize the video"
        }
    ],
    stream=True,
    stream_options={'include_usage': True},
    extra_body={
        'extra_body':
        {
            'google': {
              'cached_content': "cachedContents/0000aaaa1111bbbb2222cccc3333dddd4444eeee"
          }
        }
    }
)

for chunk in stream:
    print(chunk)
    print(chunk.usage.to_dict())

列出模型

取得可用 Gemini 模型清單：

Python

from openai import OpenAI

client = OpenAI(
  api_key="GEMINI_API_KEY",
  base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

models = client.models.list()
for model in models:
  print(model.id)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const list = await openai.models.list();

  for await (const model of list) {
    console.log(model);
  }
}
main();

REST

curl https://generativelanguage.googleapis.com/v1beta/openai/models \
-H "Authorization: Bearer GEMINI_API_KEY"

擷取模型

擷取 Gemini 模型：

Python

from openai import OpenAI

client = OpenAI(
  api_key="GEMINI_API_KEY",
  base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

model = client.models.retrieve("gemini-3-flash-preview")
print(model.id)

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
});

async function main() {
  const model = await openai.models.retrieve("gemini-3-flash-preview");
  console.log(model.id);
}

main();

REST

curl https://generativelanguage.googleapis.com/v1beta/openai/models/gemini-3-flash-preview \
-H "Authorization: Bearer GEMINI_API_KEY"

目前限制

我們正在擴大功能支援範圍，因此 OpenAI 程式庫仍處於 Beta 版。

如果您對支援的參數、即將推出的功能有任何疑問，或是在開始使用 Gemini 時遇到任何問題，請加入我們的開發人員論壇。

後續步驟

如需更詳細的範例，請試用 OpenAI 相容性 Colab。

OpenAI 相容性

Python

JavaScript

REST

思考中

Python

JavaScript

REST

Python

JavaScript

REST

串流

Python

JavaScript

REST

函式呼叫

Python

JavaScript

REST

圖像解讀

Python

JavaScript

REST

生成圖片

Python

JavaScript

REST

生成影片

Python

JavaScript

REST

查看影片狀態

Python

JavaScript

REST

音訊理解

Python

JavaScript

REST

結構化輸出內容

Python

JavaScript

嵌入

Python

JavaScript

REST

Batch API

Python

使用 extra_body 啟用 Gemini 功能

使用 extra_body 的範例

Python

列出模型

Python

JavaScript

REST

擷取模型

Python

JavaScript

REST

目前限制

後續步驟

使用 `extra_body` 啟用 Gemini 功能

使用 `extra_body` 的範例