Uncensored LLM API Documentation

Base URL and Authentication

Start by pointing your client to our specific endpoint to bypass standard content filters. Use the base URL https://api.bestabliteratedmodel.com/v1 and pass your key via the standard Authorization header. You can generate your key instantly via Google or email on the signup page without providing payment details for the trial.

Copycurl https://api.bestabliteratedmodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run the unit tests for the new authentication module"}]
  }'

Ensure your header matches the exact format above. The system validates credentials before processing any tokens, so keep your key secure.

First Request with Python SDK

Integrate directly using the official OpenAI Python library by overriding the base URL. This allows you to send prompts to the uncensored model without changing your existing code structure significantly. The model ID is always uncensored for all requests.

Copyfrom openai import OpenAI

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

This approach maintains compatibility with standard parameters like temperature and top_p. You can test the response immediately after creating the client instance.

Node.js Integration

Use the Node.js OpenAI package to send text completions to our uncensored endpoint. Set the baseURL property to our API address before making any calls. This ensures your application routes requests correctly without hitting standard provider limits.

Copyimport OpenAI from "openai";

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

Handle the response stream or single object as needed. The SDK handles tokenization internally, so you focus on prompt logic rather than infrastructure details.

Streaming with SSE

Enable real-time token generation by setting stream: true in your request parameters. The API returns Server-Sent Events (SSE) where each chunk contains partial text. Token usage metrics appear in the final chunk of the stream.

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)

Process each delta as it arrives to display text instantly to users. This reduces perceived latency significantly compared to waiting for full completion.

Function Calling and Tools

Define tool schemas in your request to enable structured output from the model. The API supports standard function definitions with parameters and descriptions. The model will return tool calls when appropriate based on your prompt instructions.

Pass the tools array with your desired functions. The response includes a tool_calls field if the model decides to invoke a tool.

JSON Mode, Limits, and Errors

Force strict JSON output by setting response_format to {"type": "json_object". This ensures reliable parsing for automated workflows. Our context window supports 100,000 tokens total, with a max output of 16,000 tokens.

Common errors include 401 for invalid keys, 402 when prepaid credit is exhausted, and 429 for rate limits (300 requests/minute). Requests for sexual content involving minors are always refused.