Responses - Python SDK
Responses method reference
(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
1 from openrouter import OpenRouter 2 import os 3 4 with OpenRouter( 5 api_key=os.getenv("OPENROUTER_API_KEY", ""), 6 ) as open_router: 7 8 res = open_router.beta.responses.send(input=[ 9 { 10 "type": "message", 11 "role": "user", 12 "content": "Hello, how are you?", 13 }, 14 ], metadata={ 15 "user_id": "123", 16 "session_id": "abc-def-ghi", 17 }, tools=[ 18 { 19 "type": "function", 20 "name": "get_current_weather", 21 "description": "Get the current weather in a given location", 22 "parameters": { 23 "type": "object", 24 "properties": { 25 "location": { 26 "type": "string", 27 }, 28 }, 29 }, 30 }, 31 ], model="anthropic/claude-4.5-sonnet-20250929", text={ 32 "format_": { 33 "type": "text", 34 }, 35 "verbosity": "medium", 36 }, reasoning={ 37 "summary": "auto", 38 "enabled": True, 39 }, temperature=0.7, top_p=0.9, prompt={ 40 "id": "<id>", 41 "variables": { 42 "key": { 43 "type": "input_text", 44 "text": "Hello, how can I help you?", 45 }, 46 }, 47 }, service_tier="auto", truncation="auto", stream=False, provider={ 48 "data_collection": "allow", 49 "zdr": True, 50 "enforce_distillable_text": True, 51 "order": [ 52 "OpenAI", 53 ], 54 "only": [ 55 "OpenAI", 56 ], 57 "ignore": [ 58 "OpenAI", 59 ], 60 "quantizations": None, 61 "sort": "price", 62 }) 63 64 with res as event_stream: 65 for event in event_stream: 66 # handle event 67 print(event, flush=True)
Parameters
| Parameter | Type | Required | Description | Example |
|---|---|---|---|---|
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_k | Optional[float] | ➖ | N/A | |
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 | |
store | OptionalNullable[bool] | ➖ | N/A | |
service_tier | OptionalNullable[components.ServiceTier] | ➖ | N/A | auto |
truncation | OptionalNullable[components.Truncation] | ➖ | N/A | auto |
stream | Optional[bool] | ➖ | N/A | |
provider | OptionalNullable[components.Provider] | ➖ | When multiple model providers are available, optionally indicate your routing preference. | |
plugins | List[components.Plugin] | ➖ | 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. | |
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 | */* |