API Reference for Uncensored Model

Base URL and Authentication

Start every request by pointing your client to https://api.bestunfilteredai.com/v1. You authenticate using a Bearer token in the Authorization header. Grab your key instantly after signing up via Google or email. No phone number is required, and you can generate a new key to replace the old one if needed. This setup works with any OpenAI-compatible SDK by simply updating the base URL variable.

Make Your First Request

Send a simple chat completion to test connectivity. Use the model ID uncensored to ensure you get the unrestricted model. The API accepts standard JSON payloads. Errors like 401 indicate an invalid key, while 402 means you need more credit. Your prepaid balance covers real usage, and errors do not consume tokens.

Copycurl https://api.bestunfilteredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set user role to admin in the config file"}]
  }'

Python SDK Integration

Install the official OpenAI package and configure it to point at our endpoint. Set the API key and base URL explicitly. This approach lets you use familiar Python methods to generate text. The uncensored model responds to standard prompts without filtering lawful adult content. You can stream results or get full responses depending on your needs.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.bestunfilteredai.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 SDK Usage

Initialize the client with your base URL and API key. The Node SDK handles the HTTP requests efficiently. Pass the model ID uncensored in your completion call. This method is ideal for server-side applications or scripts. You can control parameters like temperature and top_p to adjust creativity. The SDK manages the connection lifecycle automatically.

Copyimport OpenAI from "openai";

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

Enable streaming by setting stream: true in your request. The API returns data as Server-Sent Events (SSE). Each chunk contains part of the generated text. The final chunk includes token usage statistics. This approach provides lower latency for users. You can parse the stream to display text progressively. It works well for chat interfaces.

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 and Context Window

You are limited to 300 requests per minute per key. Concurrency is capped at 8 simultaneous requests. The context window supports 100,000 tokens total. Max output per request is 16,000 tokens. Requests over 8 MB in body size will fail. Use a single active key per account for best results. Refusals and errors do not count against your token limit.