---
title: "Create response (OpenAI Responses API)"
method: POST
path: "/v1/responses"
tags: ["Responses"]
---

# Create response (OpenAI Responses API)

`POST /v1/responses`

## Request

- Base URL: `https://api.tokenlab.sh`
- URL: `https://api.tokenlab.sh/v1/responses`
- Auth: HTTP bearer

Creates a response using the OpenAI Responses API request shape. The model details must advertise the Responses request format and the model must be available. Unknown fields are accepted on a best-effort basis; model-specific support is not guaranteed.

## Headers

- `X-TokenLab-Delivery-Policy` 'auto' | 'verified' | 'official'

## Request body

- object
  - `model` string, required: Model to use
  - `input` string: Single string input.
  - `instructions` string: System instructions
  - `max_output_tokens` integer: Maximum output tokens
  - `temperature` number
  - `stream` boolean
  - `tools` object[]: Tools available to the model. Tool types and combinations are validated by the selected service.
  - `tool_choice` union: Tool choice policy or explicit tool selection.
    - string
    - object
  - `stream_options` object: Responses streaming options.
    - `include_obfuscation` boolean: When true, request obfuscated tokens in Responses stream events where supported.
  - `include` string[]: Additional response sections to include when supported.
  - `service_tier` string, nullable: TokenLab serves this request at the standard service tier. auto and default are forwarded. Other values, such as flex, priority, fast and ultrafast, are ignored and billed at the standard price.
  - `truncation` string: Truncation strategy for long conversations.
  - `background` boolean: Whether to run the response asynchronously.
  - `previous_response_id` string: ID of a previous response to continue.
  - `prompt` object: Reference to a reusable prompt template and variables.
  - `store` boolean: Whether the response is stored for later retrieval.
  - `reasoning` object: Reasoning configuration.
  - `top_p` number: Nucleus sampling probability.
  - `parallel_tool_calls` boolean: Whether the model may issue parallel tool calls.
  - `metadata` object: Request metadata.
  - `text` object: Text formatting options.

## Response `200`

Successful response

## Other responses

- `400`: Bad Request - Invalid input
- `401`: Unauthorized - Invalid or missing API key
- `503`: The requested Delivery tier is temporarily unavailable.

---

[API](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway.md) · [All operations](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway/llms.txt) · [OpenAPI document](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway/revisions/3208bfbcda22?raw)