API Documentation & Quickstart

Base URL and Authentication

Connect immediately using your unique API key. Our base URL is https://api.unrestrictedaillm.com/v1 and requires a standard Authorization: Bearer <key> header. This setup works with any OpenAI-compatible client or SDK. You receive your key instantly after signing up with Google or email. No phone number is required. The key identifies your prepaid credit. You can generate a new key at any time, which replaces the previous one. Keep your key secure. We do not store your prompts for training. Your privacy is maintained by design. Errors in your requests do not consume credit. Only successful token generation is billed.

First Request

Send your first message to the /v1/chat/completions endpoint. The model identifier is uncensored. This open-weight model answers without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model. You get direct access to an unrestricted LLM. Streaming is available via SSE. Function calling and JSON mode are supported. The model handles complex instructions well. Context windows are large. Input and output tokens share the 100,000 token limit. Errors like bad JSON do not charge you. Refusals are free. Use the following command to verify connectivity.

Python SDK Integration

Install the official OpenAI Python package. Point it to our base URL. Pass your API key. The library handles serialization automatically. You can send system prompts to guide behavior. Temperature and top_p control randomness. Use max_tokens to cap output length. The default max is 2,048 tokens. Set it higher for long responses. Streaming yields real-time tokens. Errors raise standard exceptions. Check your balance on the dashboard. Credit never expires. You pay only for tokens used. This approach simplifies integration. Your code remains portable. Switching base URLs is trivial. Start building your unrestricted application today.

Node.js SDK Setup

Use the OpenAI Node.js SDK for JavaScript projects. Configure the base URL to our endpoint. Provide your API key in the environment. The SDK supports modern async patterns. You can stream responses easily. Function calling works with tool definitions. JSON mode ensures structured output. This is crucial for automated pipelines. The uncensored LLM handles diverse topics. No hidden filters block lawful content. Monitor your token usage. Costs are transparent. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Prepaid credit covers all usage. No monthly fees apply. Sign up with Google or email to start.

Streaming and Parameters

Enable streaming by setting stream: true. You receive chunks of text as they are generated. The final chunk contains usage statistics. This allows real-time display. Set temperature for creativity. Use top_p for nucleus sampling. Define stop sequences to halt generation. The seed parameter ensures reproducibility. Presence and frequency penalties adjust token repetition. JSON mode forces a valid object. This is useful for data extraction. Function calling lets the model invoke tools. You handle the tool execution. The uncensored LLM supports all these features. Performance is consistent. Latency is optimized for speed. Use streaming for better UX.

Rate Limits and Context Window

Our API enforces strict but fair limits. You can make 300 requests per minute. Only 8 requests run simultaneously per key. The request body must be under 8 MB. The context window holds 100,000 tokens total. This includes both prompt and completion. Max output is 16,000 tokens. If you omit max_tokens, the limit drops to 2,048. Errors return standard HTTP codes. A 401 means your key is invalid. A 402 indicates insufficient credit. A 429 signals rate limit exhaustion. Refunds are not issued for credit. Mistakes are fixed via support. Privacy is guaranteed. Your data is yours.

cURL

Copycurl https://api.unrestrictedaillm.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?"}]
  }'

Python

Copyfrom openai import OpenAI

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