Model

The Model class is the base class for all models in Agno. It provides common functionality and parameters that are inherited by specific model implementations like OpenAIChat, Claude, etc. Sampling and request parameters (temperature, max_tokens, top_p, seed, request_params, and similar) are defined on the provider classes, not on the base Model.

Parameters

Parameter	Type	Default	Description
id	str	Required	The id/name of the model to use
name	Optional[str]	None	The display name of the model
provider	Optional[str]	None	The provider of the model
model_type	ModelType	ModelType.MODEL	Functional role of this model (MODEL, OUTPUT_MODEL, or PARSER_MODEL). Set by the agent during initialization
supports_native_structured_outputs	bool	False	True if the model supports structured outputs natively (e.g. OpenAI). Set by the provider class
supports_json_schema_outputs	bool	False	True if the model requires a JSON schema for structured outputs. Set by the provider class
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 used for tool messages
assistant_message_role	str	"assistant"	Role used for assistant messages
cache_response	bool	False	Enable caching of model responses to avoid redundant API calls
cache_ttl	Optional[int]	None	Time-to-live for cached model responses, in seconds. If None, cache never expires
cache_dir	Optional[str]	None	Directory path for storing cached model responses. If None, uses default cache location
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 the model invocation with a guidance message for known errors avoidable with extra instructions
retry_with_guidance_limit	int	1	Number of times to retry the model invocation with guidance