Chat

Chat · Introduction

Protocol-oriented API docs covering two kinds of endpoints: text chat + image generation. Text is Anthropic / OpenAI compatible with SSE streaming, billed per token; the OpenAI / Gemini protocols also offer synchronous image generation (a single request returns the image, no polling) — see the "Image Generation" section on each protocol page.

Supported Protocols

Anthropic Protocol (Claude)

Anthropic Messages API compatible. For Claude models (GPT model names also work via auto protocol translation).

OpenAI Protocol (GPT)Image

OpenAI Chat Completions / Responses compatible. For GPT, plus DeepSeek, GLM, etc.

Gemini ProtocolComing SoonImage

Google Gemini generateContent compatible. Text capability implemented, in gray release, not yet open.

Streaming (SSE)

All protocols support streaming (SSE): add "stream": true. For OpenAI, also add "stream_options": {"include_usage": true} to get usage. See each protocol page.

List Models (/v1/models)

Call GET /v1/models to fetch the live list of available models for your account (OpenAI-compatible), returning each model id. Treat this endpoint as the source of truth.

curl https://api.cqtai.com/v1/models \
  -H "Authorization: Bearer <API_KEY>"

{
  "object": "list",
  "data": [
    { "id": "gpt-4o", "object": "model", "owned_by": "openai" },
    { "id": "claude-haiku-4-5-20251001", "object": "model", "owned_by": "anthropic" }
  ]
}

Model List

Available chat models and prices (per 1M tokens), same source as the pricing page. Actual cost = price × billing rate.

Loading…

Third-party Integration

Integrate via Claude Code / Codex / Gemini / CC-Switch — see CLI / VS Code setup on the left.