> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/googleapis/python-genai/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration Types

> Types for configuring API requests and behavior

## Overview

Configuration types control various aspects of API requests, including generation parameters, HTTP options, and retry behavior.

## GenerateContentConfig

Main configuration for content generation requests.

### Generation Parameters

<ParamField path="temperature" type="float">
  Controls randomness in token selection. Range: 0.0 to 2.0.

  * Lower values (e.g., 0.2): More deterministic, focused responses
  * Higher values (e.g., 1.5): More creative, diverse responses
</ParamField>

<ParamField path="top_p" type="float">
  Nucleus sampling parameter. Range: 0.0 to 1.0.
  Tokens are selected from smallest set whose cumulative probability exceeds top\_p.
</ParamField>

<ParamField path="top_k" type="float">
  Number of highest probability tokens to consider at each step.
</ParamField>

<ParamField path="max_output_tokens" type="int">
  Maximum number of tokens in the response.
</ParamField>

<ParamField path="candidate_count" type="int">
  Number of response variations to generate.
</ParamField>

<ParamField path="stop_sequences" type="list[str]">
  List of strings that stop generation when encountered.
</ParamField>

<ParamField path="seed" type="int">
  Random seed for reproducible outputs.
</ParamField>

### Response Configuration

<ParamField path="response_mime_type" type="str">
  Output format for the response.

  * `"text/plain"`: Plain text (default)
  * `"application/json"`: JSON response
</ParamField>

<ParamField path="response_schema" type="SchemaUnion">
  Schema object defining expected response structure. Use with `response_mime_type="application/json"`.
</ParamField>

<ParamField path="response_json_schema" type="Any">
  JSON Schema for response validation. Alternative to `response_schema` with full JSON Schema support.
</ParamField>

<ParamField path="response_logprobs" type="bool">
  Whether to return log probabilities of chosen tokens.
</ParamField>

<ParamField path="logprobs" type="int">
  Number of top candidate tokens to return log probabilities for.
</ParamField>

### Instructions and Tools

<ParamField path="system_instruction" type="ContentUnion">
  Instructions to steer model behavior (e.g., "Answer concisely", "You are a helpful assistant").
</ParamField>

<ParamField path="tools" type="ToolListUnion">
  List of tools the model can use (functions, code execution, search).
</ParamField>

<ParamField path="tool_config" type="ToolConfig">
  Configuration for tool usage and function calling.
</ParamField>

<ParamField path="automatic_function_calling" type="AutomaticFunctionCallingConfig">
  Configuration for automatic function calling.
</ParamField>

### Safety and Filtering

<ParamField path="safety_settings" type="list[SafetySetting]">
  Safety settings to block unsafe content.
</ParamField>

<ParamField path="model_armor_config" type="ModelArmorConfig">
  Model Armor configuration for prompt/response sanitization. Cannot be used with `safety_settings`.
</ParamField>

### Media Configuration

<ParamField path="media_resolution" type="MediaResolution">
  Default media resolution for all media in the request.
</ParamField>

<ParamField path="response_modalities" type="list[str]">
  Modalities the model can return (e.g., \["TEXT", "IMAGE", "AUDIO"]).
</ParamField>

<ParamField path="speech_config" type="SpeechConfigUnion">
  Configuration for speech generation.
</ParamField>

<ParamField path="audio_timestamp" type="bool">
  Whether to include audio timestamps in the request.
</ParamField>

<ParamField path="image_config" type="ImageConfig">
  Configuration for image generation.
</ParamField>

### Advanced Options

<ParamField path="presence_penalty" type="float">
  Penalizes tokens that have appeared, encouraging diverse content.
</ParamField>

<ParamField path="frequency_penalty" type="float">
  Penalizes frequently repeated tokens.
</ParamField>

<ParamField path="thinking_config" type="ThinkingConfig">
  Configuration for model thinking/reasoning features.
</ParamField>

<ParamField path="routing_config" type="GenerationConfigRoutingConfig">
  Configuration for model routing.
</ParamField>

<ParamField path="model_selection_config" type="ModelSelectionConfig">
  Configuration for model selection.
</ParamField>

<ParamField path="cached_content" type="str">
  Resource name of cached content to use.
</ParamField>

<ParamField path="labels" type="dict[str, str]">
  User-defined metadata labels for billing breakdown.
</ParamField>

<ParamField path="http_options" type="HttpOptions">
  HTTP request options (see below).
</ParamField>

<ParamField path="should_return_http_response" type="bool">
  Whether to return raw HTTP response in `sdk_http_response` field.
</ParamField>

### Example

```python theme={null}
from google.genai.types import GenerateContentConfig

config = GenerateContentConfig(
    temperature=0.7,
    max_output_tokens=1024,
    top_p=0.95,
    top_k=40,
    stop_sequences=["END"],
    response_mime_type="application/json",
    system_instruction="You are a helpful assistant that responds in JSON format.",
    seed=42
)

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="List 3 colors",
    config=config
)
```

## HttpOptions

HTTP request configuration.

<ParamField path="base_url" type="str">
  Base URL for the API endpoint.
</ParamField>

<ParamField path="base_url_resource_scope" type="ResourceScope">
  Resource scope for constructing resource names with custom base\_url.
</ParamField>

<ParamField path="api_version" type="str">
  API version to use.
</ParamField>

<ParamField path="headers" type="dict[str, str]">
  Additional HTTP headers.
</ParamField>

<ParamField path="timeout" type="int">
  Request timeout in milliseconds.
</ParamField>

<ParamField path="client_args" type="dict[str, Any]">
  Arguments passed to the HTTP client.
</ParamField>

<ParamField path="async_client_args" type="dict[str, Any]">
  Arguments passed to the async HTTP client.
</ParamField>

<ParamField path="extra_body" type="dict[str, Any]">
  Extra parameters to add to the request body. Must match backend API structure.
</ParamField>

<ParamField path="retry_options" type="HttpRetryOptions">
  HTTP retry configuration (see below).
</ParamField>

<ParamField path="httpx_client" type="httpx.Client">
  Custom httpx client for requests.
</ParamField>

<ParamField path="httpx_async_client" type="httpx.AsyncClient">
  Custom httpx async client.
</ParamField>

<ParamField path="aiohttp_client" type="aiohttp.ClientSession">
  Custom aiohttp client session.
</ParamField>

### Example

```python theme={null}
from google.genai.types import HttpOptions

http_options = HttpOptions(
    timeout=30000,  # 30 seconds
    headers={"X-Custom-Header": "value"},
    retry_options={
        "attempts": 3,
        "initial_delay": 1.0
    }
)

config = GenerateContentConfig(
    temperature=0.5,
    http_options=http_options
)
```

## HttpRetryOptions

Retry configuration for HTTP requests.

<ParamField path="attempts" type="int">
  Maximum number of attempts including the original request. Default: 5.
  Set to 0 or 1 for no retries.
</ParamField>

<ParamField path="initial_delay" type="float">
  Initial delay before first retry in seconds. Default: 1.0.
</ParamField>

<ParamField path="max_delay" type="float">
  Maximum delay between retries in seconds. Default: 60.0.
</ParamField>

<ParamField path="exp_base" type="float">
  Exponential backoff multiplier. Default: 2.0.
</ParamField>

<ParamField path="jitter" type="float">
  Randomness factor for delay. Default: 1.0.
</ParamField>

<ParamField path="http_status_codes" type="list[int]">
  HTTP status codes that trigger a retry.
  Default: 408, 429, and 5xx errors.
</ParamField>

### Example

```python theme={null}
from google.genai.types import HttpRetryOptions

retry_options = HttpRetryOptions(
    attempts=5,
    initial_delay=1.0,
    max_delay=60.0,
    exp_base=2.0,
    jitter=0.5,
    http_status_codes=[408, 429, 500, 502, 503, 504]
)

http_options = HttpOptions(retry_options=retry_options)
```

## Common Configuration Patterns

### Creative Writing

```python theme={null}
config = GenerateContentConfig(
    temperature=1.2,
    top_p=0.95,
    top_k=50,
    max_output_tokens=2048
)
```

### Deterministic Output

```python theme={null}
config = GenerateContentConfig(
    temperature=0.0,
    top_p=1.0,
    seed=12345,
    max_output_tokens=1024
)
```

### JSON Response

```python theme={null}
from google.genai.types import GenerateContentConfig, Schema, Type

schema = Schema(
    type=Type.OBJECT,
    properties={
        "name": Schema(type=Type.STRING),
        "age": Schema(type=Type.INTEGER),
    },
    required=["name", "age"]
)

config = GenerateContentConfig(
    response_mime_type="application/json",
    response_schema=schema
)
```

### With System Instructions

```python theme={null}
config = GenerateContentConfig(
    system_instruction="""You are a technical documentation expert.
    Provide clear, concise explanations with code examples.
    Use markdown formatting.""",
    temperature=0.3,
    max_output_tokens=2048
)
```

### With Safety Settings

```python theme={null}
from google.genai.types import (
    GenerateContentConfig,
    SafetySetting,
    HarmCategory,
    HarmBlockThreshold
)

config = GenerateContentConfig(
    safety_settings=[
        SafetySetting(
            category=HarmCategory.HARM_CATEGORY_HARASSMENT,
            threshold=HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE
        ),
        SafetySetting(
            category=HarmCategory.HARM_CATEGORY_HATE_SPEECH,
            threshold=HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE
        )
    ]
)
```

### With Custom Timeout

```python theme={null}
config = GenerateContentConfig(
    temperature=0.7,
    http_options=HttpOptions(
        timeout=60000,  # 60 seconds
        retry_options=HttpRetryOptions(attempts=3)
    )
)
```

## See Also

* [Types Overview](/api/types/overview) - Type system overview
* [Client Reference](/api/client) - Using config with the client
* [Content Types](/api/types/content) - Content and Part types