Documentation for the openai compatible api key

Authentication and base URL

Use your generated key with the provided base URL to connect instantly. The endpoint is https://api.openaicompatibleapikey.com/v1 and works with any OpenAI-compatible client. You receive one active key per account; generating a new one replaces the old. Authentication is handled via the Authorization header with the Bearer scheme. No phone number is required for signup, and you can start with a free $0.50 trial.

First request with curl

Send a simple completion to verify your connection and uncensored model. The request uses the standard POST /v1/chat/completions endpoint with the model ID set to uncensored. This confirms your API key is valid and the endpoint is reachable before you integrate it into your application. The response includes token usage and the generated text.

Copycurl https://api.openaicompatibleapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the total price including tax"}]
  }'

Python SDK integration

Integrate the API into your Python projects by overriding the default base URL. This allows you to use the official openai library with our uncensored LLM without changing your code logic. Pass your API key and the specific base URL to the client initialization. The model ID remains uncensored for all requests.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicompatibleapikey.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 integration

Connect your Node.js applications by setting the baseURL and apiKey properties. This ensures compatibility with existing OpenAI-compatible client code. You can continue using standard parameters like messages and model. The client will route requests to our hosted servers for uncensored generation.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicompatibleapikey.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 and token usage

Enable streaming by setting stream: true in your request parameters. The API returns Server-Sent Events (SSE) for real-time token delivery. Token usage details are included in the final chunk of the stream. This allows you to monitor costs and context usage as the text generates. The model supports a context window of 100,000 tokens.

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)

Rate limits, errors, and limits

Monitor your quota to avoid service interruptions. The limit is 300 requests per minute per key and 8 concurrent requests. A 401 error indicates an invalid key, while 402 signals insufficient credit. Errors and refusals are free. The context window is 100,000 tokens, with a max output of 16,000 tokens per request. Credit never expires.