> ## AI Agent Context
> Get the complete documentation index at: https://aistudio.google.com/llms.txt
> Use this file to discover all available pages.
> For the full documentation in a single file, fetch: https://aistudio.google.com/llms-full.txt

# OpenAI compatibility

Gemini models are accessible using the OpenAI libraries (Python and TypeScript /
Javascript) along with the REST API, by updating three lines of code
and using your [Gemini API key](https://aistudio.google.com/apikey). If you
aren't already using the OpenAI libraries, we recommend that you call the
[Gemini API directly](/docs/get-started).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      messages=[
          {   "role": "system",
              "content": "You are a helpful assistant."
          },
          {
              "role": "user",
              "content": "Explain to me how AI works"
          }
      ]
  )
  
  print(response.choices[0].message)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
      messages: [
          {   role: "system",
              content: "You are a helpful assistant."
          },
          {
              role: "user",
              content: "Explain to me how AI works",
          },
      ],
  });
  
  console.log(response.choices[0].message);
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $GEMINI_API_KEY" \
    -d '{
      "model": "gemini-3.8-flash",
      "messages": [
        {
          "role": "user",
          "content": "Explain to me how AI works"
        }
      ]
    }'
  ```

  What changed? Just three lines!

  *   **`api_key="GEMINI_API_KEY"`**: Replace "`GEMINI_API_KEY`" with your actual Gemini
      API key, which you can get in [Google AI Studio](https://aistudio.google.com).

  *   **`base_url="https://generativelanguage.googleapis.com/v1beta/openai/"`:** This
      tells the OpenAI library to send requests to the Gemini API endpoint instead of
      the default URL.

  *   **`model="gemini-3.8-flash"`**: Choose a compatible Gemini model


  {% /tab %}

{% /tabs %}

## Thinking  {% id="thinking" %}

Gemini models are trained to think through complex problems, leading
to significantly improved reasoning. The Gemini API comes with [thinking
parameters](/docs/thinking) which give fine grain
control over how much the model will think.

Different Gemini models have different reasoning configurations, you can see how
they map to OpenAI's reasoning efforts as follows:

| reasoning_effort (OpenAI) | thinking_level (Gemini 4) | 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` |

If no `reasoning_effort` is specified, Gemini uses the model's
default [level or budget](/docs/thinking#thinking-levels).

If you want to disable thinking, you can set `reasoning_effort` to `"none"` for
2.5 models. Reasoning cannot be turned off for Gemini 2.5 Pro, Gemini 3, or Gemini 4 models.

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      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)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
      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);
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $GEMINI_API_KEY" \
    -d '{
      "model": "gemini-3.8-flash",
      "reasoning_effort": "low",
      "messages": [
        {
          "role": "user",
          "content": "Explain to me how AI works"
        }
      ]
    }'
  ```

  Gemini thinking models also produce [thought summaries](/docs/thinking#summaries).
    You can use the [`extra_body`](/docs/openai#extra-body) field to include Gemini fields
    in your request.

  Note that `reasoning_effort` and `thinking_level`/`thinking_budget` overlap
    functionality, so they can't be used at the same time.

  {% /tab %}

  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      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)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
      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);
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```shell
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d '{
        "model": "gemini-3.8-flash",
          "messages": [{"role": "user", "content": "Explain to me how AI works"}],
          "extra_body": {
            "google": {
              "thinking_config": {
                "thinking_level": "low",
                "include_thoughts": true
              }
            }
          }
        }'
  ```

  Gemini 3 supports OpenAI compatibility for thought signatures in chat completion
    APIs. You can find the full example on the [thought signatures](/docs/thought-signatures?generate-content=true#openai) page.

  {% /tab %}

{% /tabs %}

## Streaming  {% id="streaming" %}

The Gemini API supports [streaming responses](/docs/text-generation#streaming-responses).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
    messages=[
      {
          "role": "system",
          "content": "You are a helpful assistant."
      },
      {   "role": "user",
          "content": "Hello!"
      }
    ],
    stream=True
  )
  
  for chunk in response:
      print(chunk.choices[0].delta)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
      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);
    }
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d '{
        "model": "gemini-3.8-flash",
        "messages": [
            {"role": "user", "content": "Explain to me how AI works"}
        ],
        "stream": true
      }'
  ```

  {% /tab %}

{% /tabs %}

## Function calling  {% id="function-calling" %}

Function calling makes it easier for you to get structured data outputs from
generative models and is [supported in the Gemini API](/docs/function-calling).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
    messages=messages,
    tools=tools,
    tool_choice="auto"
  )
  
  print(response)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
      messages: messages,
      tools: tools,
      tool_choice: "auto",
    });
  
    console.log(response);
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer GEMINI_API_KEY" \
  -d '{
    "model": "gemini-3.8-flash",
    "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"
  }'
  ```

  {% /tab %}

{% /tabs %}

## Image understanding  {% id="image-understanding" %}

Gemini models are natively multimodal and provide best in class performance on
[many common vision tasks](/docs/image-understanding).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
    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])
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```javascript
  import OpenAI from "openai";
  import fs from 'fs';
  
  const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
  });
  
  function encodeImage(imagePath = '') {
    try {
      const imageBuffer = fs.readFileSync(imagePath);
      return imageBuffer.toString('base64');
    } catch (error) {
      console.error("Error encoding image:", error);
      return '';
    }
  }
  
  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-3.8-flash",
        messages: messages,
      });
  
      console.log(response.choices[0]);
    } catch (error) {
      console.error("Error calling Gemini API:", error);
    }
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  bash -c '
    base64_image=$(base64 -i "Path/to/agi/image.jpeg");
    curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer GEMINI_API_KEY" \
      -d "{
        \"model\": \"gemini-3.8-flash\",
        \"messages\": [
          {
            \"role\": \"user\",
            \"content\": [
              { \"type\": \"text\", \"text\": \"What is in this image?\" },
              {
                \"type\": \"image_url\",
                \"image_url\": { \"url\": \"data:image/jpeg;base64,${base64_image}\" }
              }
            ]
          }
        ]
      }"
  '
  ```

  {% /tab %}

{% /tabs %}

## Generate an image  {% id="generate-image" %}

Generate an image using `gemini-2.5-flash-image` or `gemini-3-pro-image-preview`. Supported parameters include `prompt`, `model`, `n`, `size`, and `response_format`. Any other parameters not listed here or in the [`extra_body`](/docs/openai#extra-body) section will be silently ignored by the compatibility layer.

{% callout type="note" %}
  You can enable **Grounding with Google Search** and configure **safety settings**
  using the `extra_body` parameter. See the [`extra_body`](/docs/openai#extra-body) section
  for available parameters. Grounding with Google Search is only available on Gemini 3 and newer models.

{% /callout %}

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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()
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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);
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  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,
        }'
  ```

  {% /tab %}

{% /tabs %}

## Generate a video  {% id="generate-video" %}

{% callout type="warning" %}
   Veo 3.1 Preview (`veo-3.1-generate-preview`,
  `veo-3.1-fast-generate-preview`, and `veo-3.1-lite-generate-preview`) in the
  Gemini API was [shut down](/docs/deprecations) on **October 22, 2026**. Migrate
  to [Gemini Omni Flash](/docs/omni) (`gemini-omni-1.2-flash`) using the native
  Google GenAI SDK ([Interactions API](/docs/interactions-overview)) or the GA
  models available through the
  [Gemini Enterprise Agent Platform](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate)
  to avoid service interruptions. Video generation with `gemini-omni-1.2-flash` is
  not supported on the OpenAI-compatible `/v1/videos` endpoint. 

{% /callout %}

## Audio understanding  {% id="audio-understanding" %}

Analyze audio input:

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      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)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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 = audioFile.toString('base64');
  
  async function main() {
    const response = await client.chat.completions.create({
      model: "gemini-3.8-flash",
      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);
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  Note: If you get an `Argument list too long` error, the encoding of your
    audio file might be too long for curl.

  ```bash
  bash -c '
    base64_audio=$(base64 -i "/path/to/your/audio/file.wav");
    curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer GEMINI_API_KEY" \
      -d "{
        \"model\": \"gemini-3.8-flash\",
        \"messages\": [
          {
            \"role\": \"user\",
            \"content\": [
              { \"type\": \"text\", \"text\": \"Transcribe this audio file.\" },
              {
                \"type\": \"input_audio\",
                \"input_audio\": {
                  \"data\": \"${base64_audio}\",
                  \"format\": \"wav\"
                }
              }
            ]
          }
        ]
      }"
  '
  ```

  {% /tab %}

{% /tabs %}

## Structured output  {% id="structured-output" %}

Gemini models can output JSON objects in any [structure you define](/docs/structured-output).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      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)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash",
    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);
  ```

  {% /tab %}

{% /tabs %}

## Embeddings  {% id="embeddings" %}

Text embeddings measure the relatedness of text strings and can be generated
using the [Gemini API](/docs/embeddings). You can use
`gemini-embedding-2` for multimodal embeddings or
`gemini-embedding-001` for text-only embeddings.

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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"
  )
  
  print(response.data[0].embedding)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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",
      input: "Your text string goes here",
    });
  
    console.log(embedding);
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  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"
    }'
  ```

  {% /tab %}

{% /tabs %}

## Batch API  {% id="batch" %}

You can create [batch jobs](/docs/batch-api), submit them, and check
their status using the OpenAI library.

You'll need to prepare the JSONL file in OpenAI input format. For example:

```json
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3.8-flash", "messages": [{"role": "user", "content": "Tell me a one-sentence joke."}]}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "gemini-3.8-flash", "messages": [{"role": "user", "content": "Why is the sky blue?"}]}}
```

OpenAI compatibility for Batch supports creating a batch,
monitoring job status, and viewing batch results.

Compatibility for upload and download is currently not supported. Instead, the
following example uses the `genai` client for uploading and downloading
[files](/docs/files), the same as when using the Gemini [Batch API](/docs/batch-api#input-file).

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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)
  ```

  The OpenAI SDK also supports [generating embeddings with the Batch API](/docs/batch-api#batch-embedding). To do so, switch out the
    `create` method's `endpoint` field for an embeddings endpoint, as well as the
    `url` and `model` keys in the JSONL file:

  ```python
  # 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"
  )
  ```

  See the [Batch embedding generation](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Get_started_OpenAI_Compatibility.ipynb)
    section of the OpenAI compatibility cookbook for a complete example.

  {% /tab %}

{% /tabs %}

## Flex and Priority inference  {% id="inference" %}

The Gemini API matches OpenAI's `service_tier` parameter in name and logic,
enforcing limits and gracefully directing traffic for both the Flex and Priority
inference tiers.

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```python
  from openai import OpenAI
  
  client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
  )
  
  completion = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[
      {"role": "user", "content": "Write a short poem about clouds."}
    ],
    service_tier="priority" # Or service_tier="flex"
  )
  
  print(completion)
  ```

  When not explicitly assigned, `service_tier` defaults to `standard`, equivalent
    to `default` for OpenAI.
    Learn more about inference tiers in the [Optimization](/docs/optimization) documentation.

  {% /tab %}

{% /tabs %}

## Enable Gemini features with `extra_body` {% id="extra-body" %}

There are several features supported by Gemini that are not available in OpenAI
models but can be enabled using the `extra_body` field.

| Parameter | Type | Endpoint | Description |
| :--- | :--- | :--- | :--- |
| **`cached_content`** | Text | Chat | Corresponds to Gemini's general content cache. |
| **`thinking_config`** | Object | Chat | Corresponds to Gemini's ThinkingConfig. |
| **`aspect_ratio`** | Text | Images | Output aspect ratio (e.g., `"16:9"`, `"1:1"`, `"9:16"`). |
| **`generation_config`** | Object | Images | Gemini generation config object (e.g., `{"responseModalities": ["IMAGE"], "candidateCount": 2}`). |
| **`safety_settings`** | List | Images | Custom safety threshold filters (e.g., `[{"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}]`). |
| **`tools`** | List | Images | Enables grounding (e.g., `[{"google_search": {}}]`). Only for `gemini-3-pro-image-preview`. |

### Example using `extra_body` {% id="extra-body-example" %}

Here's an example of using `extra_body` to set `cached_content`:

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash",
      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())
  ```

  {% /tab %}

{% /tabs %}

## List models  {% id="list-models" %}

Get a list of available Gemini models:

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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);
    }
  }
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl https://generativelanguage.googleapis.com/v1beta/openai/models \
  -H "Authorization: Bearer GEMINI_API_KEY"
  ```

  {% /tab %}

{% /tabs %}

## Retrieve a model  {% id="retrieve-model" %}

Retrieve a Gemini model:

{% tabs %}
  {% tab filename="sample.py" label="Python" %}
  ```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-3.8-flash")
  print(model.id)
  ```

  {% /tab %}

  {% tab filename="sample.js" label="JavaScript" %}
  ```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-3.8-flash");
    console.log(model.id);
  }
  
  await main();
  ```

  {% /tab %}

  {% tab filename="sample.sh" label="REST" %}
  ```bash
  curl https://generativelanguage.googleapis.com/v1beta/openai/models/gemini-3.8-flash \
  -H "Authorization: Bearer GEMINI_API_KEY"
  ```

  {% /tab %}

{% /tabs %}

## Current limitations  {% id="current-limitations" %}

Support for the OpenAI libraries is still in beta while we extend feature support.

If you have questions about supported parameters, upcoming features, or run into
any issues getting started with Gemini, join our [Developer Forum](https://discuss.ai.google.dev/c/gemini-api/4).

## What's next  {% id="whats-next" %}

Try our [OpenAI Compatibility Colab](https://colab.sandbox.google.com/github/google-gemini/cookbook/blob/main/quickstarts/Get_started_OpenAI_Compatibility.ipynb) to work through more detailed
examples.