API Documentation

KiteRouter is a multi-format AI gateway that accepts requests in OpenAI, Anthropic, and Gemini native formats. Send requests using the SDK you already use, point it at KiteRouter's base URL, and KiteRouter routes the request to the best active upstream provider.

It's Just One Line

Already using the OpenAI SDK? Just point it at KiteRouter:

diff
1 import OpenAI from 'openai'
2
3 const client = new OpenAI({
4+  baseURL: 'https://kiterouter.com/api/v1',   // ← add this
5-  apiKey: 'sk-...',
6+  apiKey: 'kr-your-api-key', // ← swap your key
7 })

That's it — same SDK, same methods, now with access to 100+ models from OpenAI, Anthropic, Google, and more.

Supported API Formats

Format	Endpoint	Notes
OpenAI	`/api/v1/chat/completions`	Standard OpenAI-compatible request and response shape
Anthropic	`/api/v1/messages`	Native Anthropic Messages API format
Gemini	`/api/v1/models/{model}:generateContent`	Native Gemini API format
Streaming	Same endpoints with `stream: true`	Server-Sent Events for all formats
Models	`/api/v1/models`	Lists KiteRouter model IDs available to your key

Info: Use whichever SDK you prefer — OpenAI, Anthropic, or Gemini. KiteRouter forwards requests to upstream providers and can rewrite the public model to the mapped upstream model.

Quick Start

Create an API key in your dashboard
Set the base URL to https://kiterouter.com/api/v1
Use a KiteRouter model ID from Models or /api/v1/models
Call any supported endpoint with your existing SDK

bash

1curl https://kiterouter.com/api/v1/chat/completions \
2  -H "Authorization: Bearer kr-your-api-key" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "gpt-4o-mini",
6    "messages": [
7      {"role": "user", "content": "Say hello in one sentence."}
8    ]
9  }'

Base URL

text
1https://kiterouter.com/api/v1

Ready to start building?

Get your API key and make your first request in under a minute.