Open Responses

Base class for interacting with providers that implement the Open Responses API specification. This provides a foundation for multi-provider, interoperable LLM interfaces based on the OpenAI Responses API.

Providers that implement this spec include Ollama (v0.13.3+) and OpenRouter. Provider reference pages document only their own defaults and additions. Every parameter below is available on all of them.

Key Differences from OpenAI Responses

• Configurable base_url for pointing to different API endpoints
• Stateless by default (no previous_response_id chaining)
• Flexible api_key handling for providers that don’t require authentication

Parameters

Parameter	Type	Default	Description
id	str	"not-provided"	The ID of the model to use
name	str	"OpenResponses"	The name of the model
provider	str	"OpenResponses"	The provider of the model
model_type	ModelType	ModelType.MODEL	Functional role of the model (e.g. MODEL, OUTPUT_MODEL, PARSER_MODEL, MEMORY_MODEL). Set by the agent during initialization
supports_native_structured_outputs	bool	True	Whether the model supports native structured outputs
supports_json_schema_outputs	bool	False	Whether 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 assigned to tool messages
assistant_message_role	str	"assistant"	Role assigned to assistant messages
role_map	Dict[str, str]	{"system": "developer", "user": "user", "assistant": "assistant", "tool": "tool"}	Mapping of message roles to provider roles
vector_store_name	str	"knowledge_base"	Name of the vector store used by the file search built-in tool

Request parameters

Parameter	Type	Default	Description
include	Optional[List[str]]	None	Additional output data to include in the response (e.g. "reasoning.encrypted_content")
max_output_tokens	Optional[int]	None	Maximum number of output tokens to generate, including reasoning tokens
max_tool_calls	Optional[int]	None	Maximum number of built-in tool calls during the response
metadata	Optional[Dict[str, Any]]	None	Developer-defined metadata to associate with the response
parallel_tool_calls	Optional[bool]	None	Whether the model can run tool calls in parallel
reasoning	Optional[Dict[str, Any]]	None	Reasoning configuration (e.g. {"enabled": True})
verbosity	Optional[Literal["low", "medium", "high"]]	None	Verbosity level of the model response
reasoning_effort	Optional[Literal["minimal", "low", "medium", "high"]]	None	Reasoning effort for reasoning models
reasoning_summary	Optional[Literal["auto", "concise", "detailed"]]	None	Level of detail for reasoning summaries
store	Optional[bool]	False	Whether to store the response on the provider side. Disabled by default for compatible providers
temperature	Optional[float]	None	Controls randomness in the model’s output
top_p	Optional[float]	None	Controls diversity via nucleus sampling
truncation	Optional[Literal["auto", "disabled"]]	None	Truncation strategy when the context window is exceeded
user	Optional[str]	None	A unique identifier representing your end-user
service_tier	Optional[Literal["auto", "default", "flex", "priority"]]	None	Processing tier for the request
strict_output	bool	True	Guarantees schema adherence for structured outputs. When False, the schema is followed as a guide and output may deviate
background	Optional[bool]	None	Enables background mode for long-running tasks. The API returns immediately and the response is polled until completion. Not supported for streaming
background_poll_interval	float	2.0	Interval in seconds between polling attempts in background mode
background_max_wait	float	600.0	Maximum time in seconds to wait for a background response before cancelling it and raising an error
extra_headers	Optional[Any]	None	Additional headers to include in requests
extra_query	Optional[Any]	None	Additional query parameters to include in requests
extra_body	Optional[Any]	None	Additional body parameters to include in requests
request_params	Optional[Dict[str, Any]]	None	Additional parameters merged into the request

Client parameters

Parameter	Type	Default	Description
api_key	Optional[str]	"not-provided"	The API key for authentication
organization	Optional[str]	None	The organization ID to use for requests
base_url	Optional[Union[str, httpx.URL]]	None	The base URL of the Responses API endpoint
timeout	Optional[float]	None	Request timeout in seconds
max_retries	Optional[int]	None	Maximum number of client-level retries for failed requests
default_headers	Optional[Dict[str, str]]	None	Default headers to include in all requests
default_query	Optional[Dict[str, str]]	None	Default query parameters to include in all requests
http_client	Optional[Union[httpx.Client, httpx.AsyncClient]]	None	HTTP client instance for making requests
client_params	Optional[Dict[str, Any]]	None	Additional parameters for client configuration
client	Optional[OpenAI]	None	Pre-configured sync OpenAI client, reused across requests
async_client	Optional[AsyncOpenAI]	None	Pre-configured async OpenAI client, reused across requests

Caching parameters

Parameter	Type	Default	Description
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. None keeps cached entries forever
cache_dir	Optional[str]	None	Directory for cached responses. Defaults to ~/.agno/cache/model_responses

Retry parameters

Parameter	Type	Default	Description
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 invocation with a guidance message appended, for known errors avoidable with extra instructions
retry_with_guidance_limit	int	1	Maximum number of retries with guidance

Usage

For most use cases, prefer the provider-specific classes:

• OllamaResponses for Ollama
• OpenRouterResponses for OpenRouter

from agno.agent import Agent
from agno.models.openai import OpenResponses

agent = Agent(
    model=OpenResponses(
        id="your-model-id",
        base_url="https://your-provider.com/v1",
        api_key="your-api-key",
    ),
)

agent.print_response("Hello!")