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. 
export OPENAI_API_KEY=sk-***

​
Example

Use OpenAIResponses with your Agent: 

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

agent = Agent(
    model=OpenAIResponses(id="gpt-4o-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.

​
Params

For more information, please refer to the OpenAI Responses docs as well.
NameTypeDefaultDescription
idstr"gpt-4o"The id of the OpenAI model to use.
namestr"OpenAIResponses"The name of this response model instance.
providerstr"OpenAI"The provider of the model.
includeOptional[List[str]]NoneList of response components to include in the response.
max_output_tokensOptional[int]NoneThe maximum number of tokens to generate in the response output.
metadataOptional[Dict[str, Any]]NoneAdditional metadata to include with the request.
parallel_tool_callsOptional[bool]NoneWhether to allow parallel tool calls.
reasoningOptional[Dict[str, Any]]NoneParameters for enabling and controlling reasoning/thinking in the response.
storeOptional[bool]NoneWhether to store the output of this response request for model distillation or evals.
temperatureOptional[float]NoneControls randomness in the model's output.
top_pOptional[float]NoneControls diversity via nucleus sampling.
truncationOptional[str]NoneHow to handle content that exceeds the token limit.
userOptional[str]NoneA unique identifier representing your end-user.
response_formatOptional[Any]NoneAn object specifying the format that the model must output.
request_paramsOptional[Dict[str, Any]]NoneAdditional parameters to include in the request.
api_keyOptional[str]NoneThe API key for authenticating with OpenAI.
organizationOptional[str]NoneThe organization to use for API requests.
base_urlOptional[Union[str, httpx.URL]]NoneThe base URL for API requests.
timeoutOptional[float]NoneThe timeout for API requests.
max_retriesOptional[int]NoneThe maximum number of retries for failed requests.
default_headersOptional[Dict[str, str]]NoneDefault headers to include in all requests.
default_queryOptional[Dict[str, str]]NoneDefault query parameters to include in all requests.
http_clientOptional[httpx.Client]NoneAn optional pre-configured HTTP client.
client_paramsOptional[Dict[str, Any]]NoneAdditional parameters for client configuration.
vector_store_namestr"knowledge_base"The name of the vector store for file uploads and retrieval.
OpenAIResponses is a subclass of the Model class and has access to the same params.