---
title: "Chat Completions"
method: POST
path: "/v1/chat/completions"
---

# Chat Completions

`POST /v1/chat/completions`

## Request

- Base URL: `https://api.jarvisclaw.ai`
- URL: `https://api.jarvisclaw.ai/v1/chat/completions`
- Auth: HTTP x402

Generate chat completions with 80+ AI models (GPT, Claude, Gemini, DeepSeek). OpenAI-compatible.

## Request body

- object
  - `max_tokens` integer: Maximum tokens to generate
  - `messages` object[], required
    - `content` string, required
    - `role` 'system' | 'user' | 'assistant', required
  - `model` string, required: Model ID (e.g. gpt-4.1-nano, claude-sonnet-4-6, deepseek-chat)
  - `stream` boolean: Enable streaming responses
  - `temperature` number: Sampling temperature (0-2)

## Response `200`

Successful response

- object
  - `data` object

## Other responses

- `402`: Payment Required

---

[API](https://skmtc.dev/jarvisclaw/apis/jarvisclaw-api.md) · [All operations](https://skmtc.dev/jarvisclaw/apis/jarvisclaw-api/llms.txt) · [OpenAPI document](https://skmtc.dev/jarvisclaw/apis/jarvisclaw-api/revisions/2011c77f4e4f?raw)