Mistral | Agno

The Mistral model provides access to Mistral's language models.

Parameters

Parameter	Type	Default	Description
`id`	`str`	`"mistral-large-latest"`	The id of the Mistral model to use
`name`	`str`	`"MistralChat"`	The name of the model
`provider`	`str`	`"Mistral"`	The provider of the model
`temperature`	`Optional[float]`	`None`	Controls randomness in the model's output
`max_tokens`	`Optional[int]`	`None`	Maximum number of tokens to generate
`top_p`	`Optional[float]`	`None`	Controls diversity via nucleus sampling
`random_seed`	`Optional[int]`	`None`	Random seed for deterministic sampling
`frequency_penalty`	`Optional[float]`	`None`	Penalizes repeated token frequencies; support depends on the selected model.
`presence_penalty`	`Optional[float]`	`None`	Penalizes tokens already present; support depends on the selected model.
`stop`	`Optional[Union[str, List[str]]]`	`None`	Stop sequence or sequences forwarded to the API.
`safe_mode`	`bool`	`False`	Legacy Agno field. Current Mistral APIs use `safe_prompt` and reject `safe_mode`
`safe_prompt`	`bool`	`False`	Inject Mistral's deprecated safety prompt. Mistral recommends custom guardrails
`request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to include in the request
`api_key`	`Optional[str]`	`None`	The API key for Mistral (defaults to MISTRAL_API_KEY env var)
`endpoint`	`Optional[str]`	`None`	Declared but rejected by the current Mistral client constructor when set; leave `None`.
`max_retries`	`Optional[int]`	`None`	Declared but rejected by the current Mistral client constructor when set; leave `None`.
`timeout`	`Optional[int]`	`None`	Declared but rejected by the current Mistral client constructor when set; leave `None`.
`client_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters for client configuration
`mistral_client`	`Optional[Mistral]`	`None`	Pre-configured Mistral client
`model_type`	`ModelType`	`ModelType.MODEL`	Functional role of this model (e.g. `MODEL`, `OUTPUT_MODEL`, `PARSER_MODEL`). Set by the agent
`supports_native_structured_outputs`	`bool`	`True`	Whether the model supports structured outputs natively
`supports_json_schema_outputs`	`bool`	`False`	Whether the model uses JSON schema for structured outputs
`system_prompt`	`Optional[str]`	`None`	System prompt from the model added to the agent
`instructions`	`Optional[List[str]]`	`None`	Instructions from the model added to the agent
`tool_message_role`	`str`	`"tool"`	Role of tool messages
`assistant_message_role`	`str`	`"assistant"`	Role of assistant messages
`cache_response`	`bool`	`False`	Cache model responses to avoid redundant API calls during development
`cache_ttl`	`Optional[int]`	`None`	Time-to-live for cached responses, in seconds
`cache_dir`	`Optional[str]`	`None`	Directory for the response cache. Defaults to `~/.agno/cache/model_responses`
`retries`	`int`	`0`	Number of retries to attempt before raising a ModelProviderError
`delay_between_retries`	`int`	`1`	Delay between retries, in seconds
`exponential_backoff`	`bool`	`False`	If True, the delay between retries is doubled each time
`retry_with_guidance`	`bool`	`True`	Retry a failed model invocation once with a guidance message appended
`retry_with_guidance_limit`	`int`	`1`	Number of times to retry the model invocation with guidance

For the current Mistral Python SDK, configure client_params with server_url, timeout_ms (milliseconds), and an SDK RetryConfig as retry_config, or provide mistral_client. Keep endpoint, timeout, and max_retries unset; their Agno names are not translated to these SDK options.

Parameters

On this page