openrouter-python-sdk-retry-errors/docs/sdks/responses

Responses

(beta.responses)

Overview

beta.responses endpoints

Available Operations

• send - Create a response

send

Creates a streaming or non-streaming response using OpenResponses API format

Example Usage

from openrouter import OpenRouter
import os


with OpenRouter(
    http_referer="<value>",
    x_title="<value>",
    api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:

    res = open_router.beta.responses.send(service_tier="auto", stream=False)

    with res as event_stream:
        for event in event_stream:
            # handle event
            print(event, flush=True)

Parameters

Parameter	Type	Required	Description	Example
http_referer	Optional[str]	➖	The app identifier should be your app's URL and is used as the primary identifier for rankings. This is used to track API usage per application.
x_title	Optional[str]	➖	The app display name allows you to customize how your app appears in OpenRouter's dashboard.
input	Optional[components.OpenResponsesInput]	➖	Input for a response request - can be a string or array of items	[ { "role": "user", "content": "What is the weather today?" } ]
instructions	OptionalNullable[str]	➖	N/A
metadata	Dict[str, str]	➖	Metadata key-value pairs for the request. Keys must be ≤64 characters and cannot contain brackets. Values must be ≤512 characters. Maximum 16 pairs allowed.	{ "user_id": "123", "session_id": "abc-def-ghi" }
tools	List[components.OpenResponsesRequestToolUnion]	➖	N/A
tool_choice	Optional[components.OpenAIResponsesToolChoiceUnion]	➖	N/A
parallel_tool_calls	OptionalNullable[bool]	➖	N/A
model	Optional[str]	➖	N/A
models	List[str]	➖	N/A
text	Optional[components.OpenResponsesResponseText]	➖	Text output configuration including format and verbosity	{ "format": { "type": "text" }, "verbosity": "medium" }
reasoning	OptionalNullable[components.OpenResponsesReasoningConfig]	➖	Configuration for reasoning mode in the response	{ "summary": "auto", "enabled": true }
max_output_tokens	OptionalNullable[float]	➖	N/A
temperature	OptionalNullable[float]	➖	N/A
top_p	OptionalNullable[float]	➖	N/A
top_logprobs	OptionalNullable[int]	➖	N/A
max_tool_calls	OptionalNullable[int]	➖	N/A
presence_penalty	OptionalNullable[float]	➖	N/A
frequency_penalty	OptionalNullable[float]	➖	N/A
top_k	Optional[float]	➖	N/A
image_config	Dict[str, components.OpenResponsesRequestImageConfig]	➖	Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/features/multimodal/image-generation for more details.	{ "aspect_ratio": "16:9" }
modalities	List[components.ResponsesOutputModality]	➖	Output modalities for the response. Supported values are "text" and "image".	[ "text", "image" ]
prompt_cache_key	OptionalNullable[str]	➖	N/A
previous_response_id	OptionalNullable[str]	➖	N/A
prompt	OptionalNullable[components.OpenAIResponsesPrompt]	➖	N/A
include	List[components.OpenAIResponsesIncludable]	➖	N/A
background	OptionalNullable[bool]	➖	N/A
safety_identifier	OptionalNullable[str]	➖	N/A
service_tier	Optional[components.ServiceTier]	➖	N/A
truncation	OptionalNullable[components.Truncation]	➖	N/A	auto
stream	Optional[bool]	➖	N/A
provider	OptionalNullable[components.OpenResponsesRequestProvider]	➖	When multiple model providers are available, optionally indicate your routing preference.
plugins	List[components.OpenResponsesRequestPluginUnion]	➖	Plugins you want to enable for this request, including their settings.
user	Optional[str]	➖	A unique identifier representing your end-user, which helps distinguish between different users of your app. This allows your app to identify specific users in case of abuse reports, preventing your entire app from being affected by the actions of individual users. Maximum of 128 characters.
session_id	Optional[str]	➖	A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 128 characters.
trace	Optional[components.OpenResponsesRequestTrace]	➖	Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
retries	Optional[utils.RetryConfig]	➖	Configuration to override the default retry behavior of the client.

Response

operations.CreateResponsesResponse

Errors

Error Type	Status Code	Content Type
errors.BadRequestResponseError	400	application/json
errors.UnauthorizedResponseError	401	application/json
errors.PaymentRequiredResponseError	402	application/json
errors.NotFoundResponseError	404	application/json
errors.RequestTimeoutResponseError	408	application/json
errors.PayloadTooLargeResponseError	413	application/json
errors.UnprocessableEntityResponseError	422	application/json
errors.TooManyRequestsResponseError	429	application/json
errors.InternalServerResponseError	500	application/json
errors.BadGatewayResponseError	502	application/json
errors.ServiceUnavailableResponseError	503	application/json
errors.EdgeNetworkTimeoutResponseError	524	application/json
errors.ProviderOverloadedResponseError	529	application/json
errors.OpenRouterDefaultError	4XX, 5XX	*/*