infer0 for Developers

infer0 lets your app offer BYO-provider AI inference via OAuth 2.0. Each of your end users connects their own provider account (OpenAI, Anthropic, etc.), and you call a single API.

How it works

1. Register your app

Sign in to the infer0 dashboard and register your OAuth app at /dev/apps. You'll get a client_id and client_secret.

2. Authorization redirect

Send the user to infer0's authorization endpoint:

GET https://infer0.cgcoss.workers.dev/oauth/authorize?client_id=<client_id>&redirect_uri=<callback_url>&response_type=code

The user signs in (if needed), selects which provider to use, and approves the request. infer0 redirects back to your callback with a code parameter.

3. Exchange code for tokens

POST https://infer0.cgcoss.workers.dev/v1/oauth/token
Content-Type: application/x-www-form-urlencoded

grant_type=authorization_code
  &code=<code>
  &client_id=<client_id>
  &client_secret=<client_secret>
  &redirect_uri=<callback_url>

Returns access_token (1 hour) and refresh_token (30 days).

4. Inference

curl https://infer0.cgcoss.workers.dev/v1/chat/completions \
  -H "Authorization: Bearer <access_token>" \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://infer0.cgcoss.workers.dev/v1",
  apiKey: "<access_token>",
});

const chat = await client.chat.completions.create({
  model: "(ignored — uses user's configured model)",
  messages: [{ role: "user", content: "Hello" }],
});

Refreshing the access token

POST https://infer0.cgcoss.workers.dev/v1/oauth/refresh
Content-Type: application/x-www-form-urlencoded

grant_type=refresh_token
  &refresh_token=<refresh_token>
  &client_id=<client_id>
  &client_secret=<client_secret>

Managing provider configs

Your end users manage their own provider keys through the infer0 dashboard. Your app never sees or handles their API keys.