openrouter-python-sdk-retry-errors/docs/components/chatgenerationparams.md

ChatGenerationParams

Chat completion request parameters

Fields

Field	Type	Required	Description	Example
provider	OptionalNullable[components.ChatGenerationParamsProvider]	➖	When multiple model providers are available, optionally indicate your routing preference.
plugins	List[components.ChatGenerationParamsPluginUnion]	➖	Plugins you want to enable for this request, including their settings.
user	Optional[str]	➖	Unique user identifier	user-123
session_id	Optional[str]	➖	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]	➖	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]	✔️	List of messages for the conversation	[ { "role": "user", "content": "Hello!" } ]
model	Optional[str]	➖	Model to use for completion	openai/gpt-4
models	List[str]	➖	Models to use for completion	[ "openai/gpt-4", "openai/gpt-4o" ]
frequency_penalty	OptionalNullable[float]	➖	Frequency penalty (-2.0 to 2.0)	0
logit_bias	Dict[str, float]	➖	Token logit bias adjustments	{ "50256": -100 }
logprobs	OptionalNullable[bool]	➖	Return log probabilities	false
top_logprobs	OptionalNullable[float]	➖	Number of top log probabilities to return (0-20)	5
max_completion_tokens	OptionalNullable[float]	➖	Maximum tokens in completion	100
max_tokens	OptionalNullable[float]	➖	Maximum tokens (deprecated, use max_completion_tokens). Note: some providers enforce a minimum of 16.	100
metadata	Dict[str, str]	➖	Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)	{ "user_id": "user-123", "session_id": "session-456" }
presence_penalty	OptionalNullable[float]	➖	Presence penalty (-2.0 to 2.0)	0
reasoning	Optional[components.Reasoning]	➖	Configuration options for reasoning models	{ "effort": "medium", "summary": "concise" }
response_format	Optional[components.ResponseFormat]	➖	Response format configuration	{ "type": "json_object" }
seed	OptionalNullable[int]	➖	Random seed for deterministic outputs	42
stop	OptionalNullable[components.Stop]	➖	Stop sequences (up to 4)	[ "" ]
stream	Optional[bool]	➖	Enable streaming response	false
stream_options	OptionalNullable[components.ChatStreamOptions]	➖	Streaming configuration options	{ "include_usage": true }
temperature	OptionalNullable[float]	➖	Sampling temperature (0-2)	0.7
parallel_tool_calls	OptionalNullable[bool]	➖	N/A
tool_choice	Optional[components.ToolChoiceOption]	➖	Tool choice configuration	auto
tools	List[components.ToolDefinitionJSON]	➖	Available tools for function calling	[ { "type": "function", "function": { "name": "get_weather", "description": "Get weather" } } ]
top_p	OptionalNullable[float]	➖	Nucleus sampling parameter (0-1)	1
debug	Optional[components.DebugOptions]	➖	Debug options for inspecting request transformations (streaming only)	{ "echo_upstream_body": true }
image_config	Dict[str, components.ChatGenerationParamsImageConfig]	➖	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.	{ "aspect_ratio": "16:9" }
modalities	List[components.Modality]	➖	Output modalities for the response. Supported values are "text", "image", and "audio".	[ "text", "image" ]
cache_control	Optional[components.CacheControl]	➖	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.