Integration Guide: Uncensored LLM API

Configure your base URL and headers

The first step is pointing your client at our hosted endpoint. Use https://api.geminiunblocked.com/v1 as your base URL and set the Authorization header to Bearer YOUR_API_KEY. This works with any OpenAI-compatible SDK without changing your import statements. We run a single dedicated uncensored model, so you do not need to manage model routing or pay for unused features like embeddings. Our API key is issued instantly after signup via Google or email. No phone number is required, and the key is displayed immediately on the screen. You can replace an existing key with a new one at any time. This setup ensures your code connects to the correct uncensored endpoint.

Send your first chat completion request

Make a standard POST request to /v1/chat/completions with your messages and the model ID uncensored. The endpoint accepts standard parameters like temperature and top_p to control randomness. You get direct text output without intermediate formatting steps. Errors during processing do not consume your prepaid credit, so you can retry safely. The context window supports up to 100,000 tokens combined for prompt and completion. This allows you to process long documents without hitting limits quickly. Use this endpoint for unrestricted text generation in your applications.

Python SDK integration

Install the official OpenAI Python library and initialize the client with our base URL. Set the model parameter to uncensored for every request. This approach keeps your code identical to standard OpenAI implementations. You can adjust the max_tokens parameter to control output length. The default max output is 2,048 tokens if you do not specify a limit. Streaming is available via the stream=True flag. This method is ideal for developers who want to drop in our API without rewriting their logic. The SDK handles token counting and error retries automatically.

Node SDK integration

Use the OpenAI Node.js package with our base URL to start sending requests. Define your system prompt and user messages in the standard array format. The uncensored model ID ensures you get unrestricted responses. You can enable JSON mode by setting response_format to {"type": "json_object"}. This is useful for generating structured data without extra parsing steps. The SDK manages the HTTP connections efficiently. You do not need to handle low-level HTTP details. This integration works seamlessly with existing Node.js applications that already use OpenAI-compatible services.

Handle streaming responses via SSE

Enable streaming by setting stream=true in your request. The API returns Server-Sent Events (SSE) with incremental token updates. Each chunk contains the delta of text generated so far. The final chunk includes the full token usage statistics for the request. This feature reduces perceived latency for end-users. You can process tokens as they arrive instead of waiting for the full response. Streaming is supported in all official SDKs. Use this for real-time chat interfaces or long-form content generation. The token usage in the last chunk helps you track your prepaid credit accurately.

Understand rate limits and token costs

You are limited to 300 requests per minute and 8 concurrent requests per key. The request body size must stay under 8 MB. If you exceed these limits, you receive a 429 error. Authentication failures return a 401 error for invalid keys. Insufficient credit results in a 402 error. Pricing is transparent: $0.15 per million input tokens and $0.50 per million output tokens. You pay only for what you use, with no monthly fees. Credit never expires, so you can use it whenever needed. Errors do not charge your balance, ensuring fair usage. This structure keeps costs predictable for power users.

cURL

Copycurl https://api.geminiunblocked.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix the null pointer exception in this Java snippet"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.geminiunblocked.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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.geminiunblocked.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

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)