wassname/openrouter-python-sdk-retry-errors
1
0
Fork 0
mirror of https://github.com/wassname/openrouter-python-sdk-retry-errors.git synced 2026-07-31 12:30:30 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
7b8f5941c8acd2b8f56cd3f0847d304b222235a0
openrouter-python-sdk-retry…/docs/components/chatgenerationparams.md
T
OpenRouter Team 7b8f5941c8 Commits included in this export: 
- 50539a3577b5a7e925b756f6bb87744052701215
  - 2cdbe64441ce4435ea0a1ff9127472e815fdaccf
  - f35bb49a8b788937fa61c0cf4591b14f2bc8b217
  - 08a37babde9ad8df5e24e0cd865d3292b1627464
  - 7ddc8e1ed230ca489bc11a5e14696c209ea76349
  - ad31290f38f3f02627f3e1953f1d7cf3e06159a5
  - fb7f764b500618e322f56d49997fbcfaebba7e39
  - 4306c032b9b4f3cfefeacdd3d243b0336f3b2f15

GitOrigin-RevId: 50539a3577b5a7e925b756f6bb87744052701215
2026-03-12 15:49:53 +00:00

40 lines
38 KiB
Markdown
Raw Blame History

# ChatGenerationParams
Chat completion request parameters
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `provider` | [OptionalNullable[components.ChatGenerationParamsProvider]](../components/chatgenerationparamsprovider.md) | :heavy_minus_sign: | When multiple model providers are available, optionally indicate your routing preference. | |
| `plugins` | List[[components.ChatGenerationParamsPluginUnion](../components/chatgenerationparamspluginunion.md)] | :heavy_minus_sign: | Plugins you want to enable for this request, including their settings. | |
| `user` | *Optional[str]* | :heavy_minus_sign: | Unique user identifier | user-123 |
| `session_id` | *Optional[str]* | :heavy_minus_sign: | A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 128 characters. | |
| `trace` | [Optional[components.ChatGenerationParamsTrace]](../components/chatgenerationparamstrace.md) | :heavy_minus_sign: | Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations. | |
| `messages` | List[[components.Message](../components/message.md)] | :heavy_check_mark: | List of messages for the conversation | [<br/>{<br/>"role": "user",<br/>"content": "Hello!"<br/>}<br/>] |
| `model` | *Optional[str]* | :heavy_minus_sign: | Model to use for completion | openai/gpt-4 |
| `models` | List[*str*] | :heavy_minus_sign: | Models to use for completion | [<br/>"openai/gpt-4",<br/>"openai/gpt-4o"<br/>] |
| `frequency_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Frequency penalty (-2.0 to 2.0) | 0 |
| `logit_bias` | Dict[str, *float*] | :heavy_minus_sign: | Token logit bias adjustments | {<br/>"50256": -100<br/>} |
| `logprobs` | *OptionalNullable[bool]* | :heavy_minus_sign: | Return log probabilities | false |
| `top_logprobs` | *OptionalNullable[float]* | :heavy_minus_sign: | Number of top log probabilities to return (0-20) | 5 |
| `max_completion_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum tokens in completion | 100 |
| `max_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16. | 100 |
| `metadata` | Dict[str, *str*] | :heavy_minus_sign: | Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values) | {<br/>"user_id": "user-123",<br/>"session_id": "session-456"<br/>} |
| `presence_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Presence penalty (-2.0 to 2.0) | 0 |
| `reasoning` | [Optional[components.Reasoning]](../components/reasoning.md) | :heavy_minus_sign: | Configuration options for reasoning models | {<br/>"effort": "medium",<br/>"summary": "concise"<br/>} |
| `response_format` | [Optional[components.ResponseFormat]](../components/responseformat.md) | :heavy_minus_sign: | Response format configuration | {<br/>"type": "json_object"<br/>} |
| `seed` | *OptionalNullable[int]* | :heavy_minus_sign: | Random seed for deterministic outputs | 42 |
| `stop` | [OptionalNullable[components.Stop]](../components/stop.md) | :heavy_minus_sign: | Stop sequences (up to 4) | [<br/>""<br/>] |
| `stream` | *Optional[bool]* | :heavy_minus_sign: | Enable streaming response | false |
| `stream_options` | [OptionalNullable[components.ChatStreamOptions]](../components/chatstreamoptions.md) | :heavy_minus_sign: | Streaming configuration options | {<br/>"include_usage": true<br/>} |
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | Sampling temperature (0-2) | 0.7 |
| `parallel_tool_calls` | *OptionalNullable[bool]* | :heavy_minus_sign: | N/A | |
| `tool_choice` | [Optional[components.ToolChoiceOption]](../components/toolchoiceoption.md) | :heavy_minus_sign: | Tool choice configuration | auto |
| `tools` | List[[components.ToolDefinitionJSON](../components/tooldefinitionjson.md)] | :heavy_minus_sign: | Available tools for function calling | [<br/>{<br/>"type": "function",<br/>"function": {<br/>"name": "get_weather",<br/>"description": "Get weather"<br/>}<br/>}<br/>] |
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | Nucleus sampling parameter (0-1) | 1 |
| `debug` | [Optional[components.DebugOptions]](../components/debugoptions.md) | :heavy_minus_sign: | Debug options for inspecting request transformations (streaming only) | {<br/>"echo_upstream_body": true<br/>} |
| `image_config` | Dict[str, [components.ChatGenerationParamsImageConfig](../components/chatgenerationparamsimageconfig.md)] | :heavy_minus_sign: | Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details. | {<br/>"aspect_ratio": "16:9"<br/>} |
| `modalities` | List[[components.Modality](../components/modality.md)] | :heavy_minus_sign: | Output modalities for the response. Supported values are "text", "image", and "audio". | [<br/>"text",<br/>"image"<br/>] |
| `cache_control` | [Optional[components.CacheControl]](../components/cachecontrol.md) | :heavy_minus_sign: | Enable automatic prompt caching. When set, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | |
Reference in New Issue View Git Blame Copy Permalink