Quickstart

RelayModels gives you unified access to 41 models through a single key. The API is OpenAI-compatible: only two lines change in your project — the base URL and the key. Everything else stays the same.

Three ways to get started

  • Automatic setup — the “Connect app” button in your dashboard: pick a tool and the script writes the URL and key for you.
  • Ready-made client — the official OpenAI libraries for Python and Node.js: just point them at our base URL.
  • Plain HTTP request — works from any language, no dependencies required.

Basic parameters

API base URLhttps://api.relaymodels.com/v1
AuthorizationAuthorization: Bearer <key>
FormatOpenAI-compatible (chat completions)

Your first request

curl https://api.relaymodels.com/v1/chat/completions \
  -H "Authorization: Bearer $RELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
The model name is the only thing that changes between models. See the full list in Models.

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RELAY_API_KEY"],
    base_url="https://api.relaymodels.com/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RELAY_API_KEY,
  baseURL: "https://api.relaymodels.com/v1",
});

const res = await client.chat.completions.create({
  model: "gpt-5.6-sol",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(res.choices[0].message.content);

What's next