Integrate the uncensored model

Base URL and authentication

Connect your client to our dedicated gateway using the provided base URL. All requests require a valid API key passed in the Authorization header. This setup works with any OpenAI-compatible SDK without modifying your core logic.

Sign up for a key via Google or email on the Get API key page. The key appears immediately, allowing you to start testing without phone verification. Keep your credentials secure, as they grant access to your prepaid credit.

Making your first request

Send a standard chat completion request to generate text. Use the model identifier uncensored to access our open-weight model tuned for unrestricted responses.

Copycurl https://api.openrouterpricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the hourly rate for each model tier."}]
  }'

Ensure your payload includes the model field and your messages array. The API returns JSON with the generated content, ready for your application logic.

Python SDK integration

Use the official OpenAI Python library to interact with our API. Point the client to our base URL and inject your API key. This approach keeps your code clean and leverages existing community support for the standard library.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openrouterpricing.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)

Initialize the client with your key and the custom base URL. Call the chat completions endpoint just as you would for other models, but with the uncensored model ID.

Node SDK integration

Integrate directly into your JavaScript or TypeScript projects using the Node OpenAI SDK. Set the baseURL and apiKey properties to route requests correctly. This method ensures type safety and easy error handling in modern web apps.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openrouterpricing.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);

Configure the SDK instance with your credentials. Send messages and receive responses using standard async/await patterns, fitting seamlessly into your existing Node.js architecture.

Streaming responses

Enable streaming by setting stream to true in your request. This returns a Server-Sent Events (SSE) stream, allowing you to display tokens as they generate. It reduces perceived latency for end-users and improves interactivity.

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)

Parse the SSE chunks to update your UI in real-time. The final chunk contains the total token usage, which is billed against your prepaid credit. Errors during streaming do not incur charges.

Limits, errors, and context

Monitor your rate limits and handle errors gracefully. You are allowed 300 requests per minute and 8 concurrent requests per key. If you exceed these, you receive a 429 status code. A 401 error indicates an invalid key, while a 402 error means you need to top up your credit.

The model supports a context window of 100,000 tokens for both input and output combined. Max output is capped at 16,000 tokens unless specified otherwise. Keep your requests within these bounds to avoid truncation or errors.