Documentation / App integrations

Use cheaper inference in the apps you already know

Cheaper Inference supports OpenAI-compatible Chat Completions, a stateless Responses API for Codex, and an Anthropic-compatible Messages API for Claude Code. Most agents, coding tools, and chat apps only need a base URL, an API key, and a model ID.

Connection basics

Use this base URL

https://api.cheaperinference.com/v1

Before you start

Create an API key, then copy an exact model ID from the live model catalog. Store keys in an environment variable when the app supports it.

OpenAI Node

OpenAI Node SDK

1import OpenAI from "openai";23const client = new OpenAI({4  apiKey: process.env.CHEAPER_INFERENCE_API_KEY,5  baseURL: "https://api.cheaperinference.com/v1",6});78const response = await client.chat.completions.create({9  model: "gpt-5.4",10  messages: [{ role: "user", content: "Hello" }],11});