An OpenAI-compatible API for every major model

Keep your existing OpenAI SDK code. Change the base URL and API key, then pick any model in the catalogue or let the auto router choose.

Drop-in /v1/chat/completions with server-sent-event streaming
GET /v1/models lists every model id you can request
One secret and one bill across providers instead of a key per vendor
Automatic fallbacks if a provider is down
Works with the OpenAI Python and JavaScript SDKs, LangChain, LlamaIndex and curl

Quick start

curl

curl https://api.text-generator.io/v1/chat/completions \
  -H "Authorization: Bearer $TEXT_GENERATOR_SECRET" \
  -H "Content-Type: application/json" \
  -d '{"model":"text-generator/auto","messages":[{"role":"user","content":"Write a haiku about routers"}]}'

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_SECRET", base_url="https://api.text-generator.io/v1")
resp = client.chat.completions.create(
    model="text-generator/auto",
    messages=[{"role": "user", "content": "Write a haiku about routers"}],
)
print(resp.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({ apiKey: process.env.TEXT_GENERATOR_SECRET, baseURL: "https://api.text-generator.io/v1" });
const resp = await client.chat.completions.create({
  model: "text-generator/auto",
  messages: [{ role: "user", content: "Write a haiku about routers" }],
});
console.log(resp.choices[0].message.content);

Pricing

Cloud plan $19/month or $190/year; pay-as-you-go API credits at $0.01 each; self-hosting the open source stack is free. Model rates are listed per 1M tokens at https://text-generator.io/models. See pricing

FAQ

Is the API OpenAI compatible?

Yes. Point any OpenAI SDK at https://api.text-generator.io/v1 and use your Text Generator secret as the API key. Chat completions, streaming and model listing use the OpenAI request and response format.

How much does it cost?

Cloud plan $19/month or $190/year; pay-as-you-go API credits at $0.01 each; self-hosting the open source stack is free. Model rates are listed per 1M tokens at https://text-generator.io/models.

Can I self-host it?

Yes. The stack is open source at github.com/TextGeneratorio/text-generator.io and can be self-hosted for free.