Developers

Drop-in for any OpenAI SDK

Run the Zintus gateway locally and change two lines in your existing code. Requests route across 12 free providers with automatic failover — your keys never leave your machine.

$ bun install && bun run --filter zintus build  # npm publish coming soon
$ zintus serve   # starts the gateway on :8788

Two-line change

OpenAI SDK (Node)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://localhost:8788/v1", // your local Zintus gateway
  apiKey: "any-string",                 // gateway uses your local keys
});

const res = await openai.chat.completions.create({
  model: "auto",                        // or a provider/model id
  messages: [{ role: "user", content: "Hello!" }],
  stream: true,
});

Vercel AI SDK

import { createOpenAI } from "@ai-sdk/openai";

const zintus = createOpenAI({
  baseURL: "http://localhost:8788/v1",
  apiKey: "any-string",
});

const { textStream } = streamText({
  model: zintus("auto"),
  prompt: "Explain routing in one line.",
});

Python

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8788/v1",
    api_key="any-string",
)

stream = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

Works with

OpenAI SDKVercel AI SDKLangChainLlamaIndexAny OpenAI-compatible client

Full API reference lives in the docs.

zintus

StarOpen app