Claude | Agno

The Claude model provides access to Anthropic's Claude models.

Parameters

Parameter	Type	Default	Description
`id`	`str`	`"claude-sonnet-4-5-20250929"`	The id of the Anthropic Claude model to use
`name`	`str`	`"Claude"`	The name of the model
`provider`	`str`	`"Anthropic"`	The provider of the model
`max_tokens`	`Optional[int]`	`8192`	Maximum number of tokens to generate in the chat completion
`thinking`	`Optional[Dict[str, Any]]`	`None`	Configuration for the thinking (reasoning) process
`output_config`	`Optional[Dict[str, Any]]`	`None`	Output configuration sent as the `output_config` request parameter
`temperature`	`Optional[float]`	`None`	Controls randomness in the model's output
`stop_sequences`	`Optional[List[str]]`	`None`	A list of strings that the model should stop generating text at
`top_p`	`Optional[float]`	`None`	Controls diversity via nucleus sampling
`top_k`	`Optional[int]`	`None`	Controls diversity via top-k sampling
`cache_system_prompt`	`Optional[bool]`	`False`	Whether to cache the system prompt for improved performance
`extended_cache_time`	`Optional[bool]`	`False`	Whether to use extended cache time (1 hour instead of default)
`cache_tools`	`bool`	`False`	Tag the last tool definition with cache control so tool definitions are cached
`system_prompt_blocks`	`Optional[Union[List[SystemPromptBlock], Callable[[], List[SystemPromptBlock]]]]`	`None`	Multi-block system prompt with per-block cache control, appended after the agent-built system message in the Anthropic `system` array. Callables are evaluated on every request, allowing dynamic per-request content in a cached system prompt
`request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to include in the request
`betas`	`Optional[List[str]]`	`None`	Anthropic beta flags enabling experimental or newly released features. Betas required for skills and structured outputs are added automatically
`context_management`	`Optional[Dict[str, Any]]`	`None`	Context management configuration sent as the `context_management` request parameter
`mcp_servers`	`Optional[List[MCPServerConfiguration]]`	`None`	List of MCP (Model Context Protocol) server configurations
`skills`	`Optional[List[Dict[str, str]]]`	`None`	Claude Agent Skills to enable, e.g. `[{"type": "anthropic", "skill_id": "pptx", "version": "latest"}]`. Adds the required beta flags automatically
`citations`	`bool`	`True`	Attach citations to document blocks. Suppressed automatically when structured output is active because Anthropic rejects citations together with `output_format`
`append_trailing_user_message`	`Optional[bool]`	`None`	Append a trailing user turn after an assistant message. When `None`, enabled for models without prefill support and whenever effective thinking is enabled, including a `request_params` thinking override.
`trailing_user_message_content`	`str`	`"continue"`	Content of the appended trailing user message
`api_key`	`Optional[str]`	`None`	The API key for authenticating with Anthropic (defaults to ANTHROPIC_API_KEY env var)
`auth_token`	`Optional[str]`	`None`	Auth token for the Anthropic client. Falls back to the `ANTHROPIC_AUTH_TOKEN` environment variable
`default_headers`	`Optional[Dict[str, Any]]`	`None`	Default headers to include in all requests
`timeout`	`Optional[float]`	`None`	Request timeout in seconds
`http_client`	`Optional[Union[httpx.Client, httpx.AsyncClient]]`	`None`	Custom httpx client to use for requests
`client_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters for client configuration
`client`	`Optional[AnthropicClient]`	`None`	A pre-configured instance of the Anthropic client
`async_client`	`Optional[AsyncAnthropicClient]`	`None`	A pre-configured instance of the async Anthropic client
`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`	Set to True automatically for Claude models that support native structured outputs
`supports_json_schema_outputs`	`bool`	`False`	True if the model requires a 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 used for tool messages
`assistant_message_role`	`str`	`"assistant"`	Role used for 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 model responses, in seconds. If None, cache never expires
`cache_dir`	`Optional[str]`	`None`	Directory for cached model responses. If None, uses the 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

Parameters

On this page