API reference

Chat Completions

OpenAI-compatible /v1/chat/completions — the endpoint most SDKs call by default.

Overview

The OpenAI-compatible chat completions endpoint — the default call for most SDKs and coding agents.

Method: POST
Path: /v1/chat/completions
Auth: Authorization: Bearer <KUMO_API_KEY>

Request

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

curl https://api.kumo.cloud/v1/chat/completions \
  -H "Authorization: Bearer $KUMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-4",
    "messages": [{ "role": "user", "content": "Explain tokens in one line." }]
  }'

Response

A standard chat.completion object. The reply text is in choices[0].message.content, exact token counts are in usage.

{
  "id": "chatcmpl-8f2b7e10c9",
  "object": "chat.completion",
  "model": "claude-sonnet-4-6",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "..." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 18, "total_tokens": 30 }
}

PreviousPricing & billing NextResponses