OpenAI Responses

Use OpenAI’s Responses API with Agno agents.

OpenAIResponses is a class for interacting with OpenAI models using the Responses API. This class provides a streamlined interface for working with OpenAI’s newer Responses API, which is distinct from the traditional Chat API. It supports advanced features like tool use, file processing, and knowledge retrieval.

Authentication

Set your OPENAI_API_KEY environment variable. You can get one from OpenAI here.

Mac

export OPENAI_API_KEY=sk-***

setx OPENAI_API_KEY sk-***

Example

Use OpenAIResponses with your Agent:

agent.py

from agno.agent import Agent
from agno.media import File
from agno.models.openai.responses import OpenAIResponses

agent = Agent(
    model=OpenAIResponses(id="gpt-5-mini"),
    tools=[{"type": "file_search"}, {"type": "web_search_preview"}],
    markdown=True,
)

agent.print_response(
    "Summarize the contents of the attached file and search the web for more information.",
    files=[File(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf")],
)

View more examples here.

Parameters

For more information, please refer to the OpenAI Responses docs as well.

Parameter	Type	Default	Description
id	str	"gpt-5-mini"	The id of the OpenAI model to use with Responses API
name	str	"OpenAIResponses"	The name of the model
provider	str	"OpenAI"	The provider of the model
instructions	Optional[str]	None	System-level instructions for the assistant
response_format	Optional[Union[str, Dict]]	None	Response format specification for structured outputs
temperature	Optional[float]	None	Controls randomness in the model’s output (0.0 to 2.0)
top_p	Optional[float]	None	Controls diversity via nucleus sampling (0.0 to 1.0)
max_completion_tokens	Optional[int]	None	Maximum number of completion tokens to generate
truncation_strategy	Optional[Dict[str, Any]]	None	Strategy for truncating messages when they exceed context limits
tool_choice	Optional[Union[str, Dict]]	None	Controls which function is called by the model
parallel_tool_calls	Optional[bool]	None	Whether to enable parallel function calling
metadata	Optional[Dict[str, str]]	None	Developer-defined metadata to associate with the response
strict_output	bool	True	Controls schema adherence for structured outputs
api_key	Optional[str]	None	The API key for authenticating with OpenAI (defaults to OPENAI_API_KEY env var)
organization	Optional[str]	None	The organization ID to use for requests
base_url	Optional[Union[str, httpx.URL]]	None	The base URL for the OpenAI API
timeout	Optional[float]	None	Request timeout in seconds
max_retries	Optional[int]	None	Maximum number of retries for failed requests
default_headers	Optional[Any]	None	Default headers to include in all requests
http_client	Optional[Union[httpx.Client, httpx.AsyncClient]]	None	HTTP client instance for making requests

OpenAIResponses is a subclass of the Model class and has access to the same params.