Skip to content

API reference

Responses

OpenAI-compatible /v1/responses — the newer stateful-friendly response format.

Overview

The OpenAI-compatible Responses API — a newer response format with a single output list instead of choices.

Method
Path
/v1/responses
Auth
Authorization: Bearer <KUMO_API_KEY>

Request

Base URL: https://api.kumo.cloud/v1

curl https://api.kumo.cloud/v1/responses \
  -H "Authorization: Bearer $KUMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-4",
    "input": "Explain tokens in one line."
  }'

Response

The reply text is assembled in output[0].content[0].text (or available via the SDK's resp.output_text convenience field); exact token counts are in usage.

{
  "id": "resp_8f2b7e10c9",
  "object": "response",
  "model": "gpt-5-4",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [{ "type": "output_text", "text": "..." }]
    }
  ],
  "usage": { "input_tokens": 12, "output_tokens": 18, "total_tokens": 30 }
}