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 when the conversation ends with an assistant message. Defaults to True for models without prefill support (Claude 4.6+) |
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 |
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 |
