OpenAI-Compatible Endpoints Documentation

Authentication and Base URL

Start by generating your API key via the dashboard using your Google account or email. Append this key to every request header as Authorization: Bearer YOUR_API_KEY. The base URL is https://api.openaicompatibleendpoints.com/v1, ensuring your existing client code works without modification. You receive one active key per account, which you can regenerate instantly if compromised. No phone number is required for signup, keeping the process fast and private.

First Request

Send a standard chat completion request to begin generating text immediately. This confirms your credentials and token balance are active before scaling up your workflow. The endpoint accepts standard JSON payloads identical to the OpenAI format, allowing you to test connectivity with minimal overhead.

Copycurl https://api.openaicompatibleendpoints.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the current server time in UTC format"}]
  }'

Python SDK Integration

Install the official OpenAI Python package and point it at our base URL to leverage familiar patterns. This approach works seamlessly with tools like LangChain or LlamaIndex that expect OpenAI-compatible endpoints. You can switch models or providers by simply updating the base URL configuration without changing your application logic. This flexibility is critical for agencies managing multiple inference pipelines.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicompatibleendpoints.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 Usage

Initialize the Node.js client with your base URL and API key to start streaming or synchronous requests. This setup mirrors the standard OpenAI client interface, making it easy to integrate into Express or Fastify applications. You can handle errors gracefully by checking the status codes returned by the server, ensuring your application remains robust during high-volume usage.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicompatibleendpoints.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 (SSE)

Enable streaming by setting the stream parameter to true, which returns data in real-time via Server-Sent Events. This reduces perceived latency for end-users, especially when generating long responses or complex reasoning chains. Each chunk contains partial content, allowing you to render text progressively in your interface. The final chunk includes the complete token usage statistics for accurate billing tracking.

Copystream = 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, and Context

Your API key supports up to 300 requests per minute and allows 8 concurrent connections. If you exceed these limits, the server returns a 429 status code; insufficient funds trigger a 402 error, while invalid keys result in a 401. The model handles a context window of 100,000 tokens, combining prompt and completion. Errors and refusals do not consume your prepaid credit, ensuring you only pay for valid inference.