---
title: "Create Response"
method: POST
path: "/v1/responses"
---

# Create Response

`POST /v1/responses`

Creates a model response for the given input using the Responses API.

## Request body

- object
  - `model` 'gpt-5.6-terra', required — Model ID for the balanced GPT-5.6 Terra tier.
  - `input` object[], required — Text or image input for the model to generate a response.
    - `role` 'user' | 'assistant' | 'system', required
    - `content` string, required
  - `stream` boolean — If true, stream partial response deltas using SSE.
  - `temperature` number — Sampling temperature. Higher values make output more random.
  - `frequency_penalty` number — Penalizes repeated tokens based on their frequency in the text so far.
  - `presence_penalty` number — Penalizes tokens that have already appeared in the text.
  - `max_output_tokens` integer — The maximum number of output tokens to generate.
  - `stop` string — Sequences where the model will stop generating further tokens.
  - `n` integer — How many response choices to generate.
  - `text` object — Configuration options for model text response.
    - `format` object
      - `type` 'text' | 'json_object' — The defined response format type.
    - `verbosity` 'low' | 'medium' | 'high' — Limits the verbosity of the model response. Default is medium.
  - `reasoning` object — Configuration for model reasoning / thinking.
    - `effort` 'none' | 'low' | 'medium' | 'high' | 'xhigh' | 'max' — Reasoning effort level. Default is medium.
    - `summary` 'auto' | 'concise' | 'detailed' — Summary of reasoning performed by the model.
    - `mode` 'pro' — Enables Pro mode for quality-first requests when set to pro.
    - `context` 'auto' | 'all_turns' | 'current_turn' — Controls whether prior reasoning is reused across turns.
  - `tools` object[] — A list of tools the model may call.
  - `prompt_cache_options` object — Options for explicit prompt caching when supported.
  - `tool_choice` string — Controls which (if any) tool is called by the model.
  - `store` boolean — Whether to store the generated model response for later retrieval via API.
  - `safety_identifier` string — Stable privacy-preserving identifier for the end user, used by safety systems.
  - `user` string — A unique identifier representing your end-user.

## Response `200`

Response generated successfully

- ResponseObject
  - `id` string, required
  - `object` string, required
  - `created_at` integer, required — Unix timestamp when the response was created.
  - `completed_at` integer — Unix timestamp when the response was completed.
  - `model` string, required
  - `status` 'completed' | 'failed' | 'in_progress' | 'incomplete', required
  - `output` object[], required
    - `id` string
    - `type` string
    - `role` string
    - `status` string
    - `content` object[]
      - `type` string
      - `text` string
      - `annotations` object[]
  - `reasoning` object
    - `effort` string
    - `summary` string
  - `text` object
    - `format` object
      - `type` string
    - `verbosity` string
  - `usage` object, required
    - `input_tokens` integer
    - `input_tokens_details` object
      - `cached_tokens` integer
    - `output_tokens` integer
    - `output_tokens_details` object
      - `reasoning_tokens` integer
    - `total_tokens` integer

## Other responses

- `400` — Invalid request
- `401` — Unauthorized
- `429` — Rate limit exceeded

---

[API](https://skmtc.net/anyfast/apis/anthropic-claude-compatible-endpoint.md) · [All operations](https://skmtc.net/anyfast/apis/anthropic-claude-compatible-endpoint/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/anyfast/anthropic-claude-compatible-endpoint/versions/edfc53e182a1/schema)