Is this the official OpenAI reverse proxy?

No, we are an independent service running our own tuned uncensored model. We do not route traffic through OpenAI, Anthropic, or any other vendor. We simply provide an OpenAI-compatible endpoint structure.

Does the API support image or audio generation?

No, we only provide text-based chat completions. There are no embeddings, image, audio, or video generation endpoints available.

What happens if I exceed the rate limit?

You will receive a 429 Too Many Requests error. You can retry after the specified delay or upgrade your usage tier if available. The limit is 300 requests per minute per key.

Docs - OpenAI Compatible Endpoint Guide

Authentication & Base URL

The base URL for this API is HTTPS://api.openaireverseproxy.com/v1. You must include your API key in the Authorization header for every request. This setup works with the official OpenAI SDKs and any OpenAI-compatible client by changing the base_url and API key.

First Request

Send a POST request to /v1/chat/completions with the model set to "uncensored". This returns text output based on your input prompt. You can test connectivity immediately with the following command:

curl https://api.openaireverseproxy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Replace YOUR_API_KEY with your key from the dashboard.

Python SDK Integration

Install the official OpenAI package and configure the base URL. The client handles authentication automatically using your API key. This ensures compatibility with existing codebases that rely on the standard OpenAI interface.

from openai import OpenAI

client = OpenAI(base_url="https://api.openaireverseproxy.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node SDK Setup

Use the official Node.js client to integrate with your JavaScript or TypeScript applications. Set the API key and base URL in the configuration object. The SDK handles the HTTP requests and response parsing efficiently.

import OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming Responses

Enable streaming by setting stream to true in your request body. The API returns chunks of data as they are generated, allowing for real-time user experiences. Token usage details are included in the final chunk.

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Limits & Errors

You are limited to 300 requests per minute and 8 concurrent requests per key. The context window is 100,000 tokens total, with a max output of 16,000 tokens. Errors include 401 for invalid keys, 402 for no credit, and 429 for rate limits.

OpenAI Compatible Endpoint Guide