API docs

This platform is a multi-protocol AI gateway — use the OpenAI, Anthropic or Google Gemini SDK you already have to call 90+ leading models (Claude / GPT / Gemini / Grok / DeepSeek / Doubao / Kimi / Qwen / MiniMax / GLM / Hunyuan), plus image, video, embedding and knowledge-base APIs. No code changes.

Start in 5 minutes Compatibility matrix

Getting started

Quickstart

Up in 5 minutes, all three SDKs, and a model cheat sheet

SDK guides

OpenAI SDK

Full Python / TypeScript / curl examples, plus cross-vendor calls

Anthropic SDK

Full examples, and why the base URL has no /v1

Gemini SDK

Full examples, multimodal input, and cross-vendor calls

Client integrations

Claude Code

Switch with a single ANTHROPIC_BASE_URL env var

Cursor

Configuring a custom OpenAI base URL

Cline

OpenAI Compatible Provider

Continue.dev

Configuring several models in config.json

Open WebUI

Connecting a self-hosted ChatGPT-like UI

New API

FlopCode

The official fork — zero configuration

Reference

Models

90+ callable models × pricing × context × capabilities

Compatibility matrix

Model family × the four client protocols: native, translated or unsupported

API reference

Request/response schemas for every endpoint, with curl examples

Image / video APIs

Images per image, video per second, and the embeddings endpoint

Digital human / smart clip APIs

Knowledge base API & MCP

Read-only knowledge search over REST, plus MCP

Agent API (organizations)

Authentication

Key format, four auth methods, and how billing works

Error codes

What 400 / 401 / 402 / 502 mean, and how to debug them

Guides

Streaming

Parsing SSE, handling interruptions, and when stream=true is required

Tool calling

How Function Tools / Tool Use / Function Calling line up

Image-to-image editing

Migrating from OpenAI

You only change two lines

Migrating from Anthropic

From the Anthropic SDK's point of view