API Documentation

Authentication

Your API key authenticates every request. Pass it in the Authorization header as a Bearer token. The key is generated immediately after signup via Google or email. Keep it secure; anyone with the key can spend your prepaid credit.

Endpoints and Request Format

Interact with the model through the standard chat completions endpoint. Use POST /v1/chat/completions to send messages and receive responses. The base URL is https://api.bestllmfornsfw.com/v1. You must specify the model ID as uncensored in your request body. We do not support embeddings, images, or fine-tuning endpoints. If you need those features, this API is not for you.

Response Format and Streaming

Responses follow the standard OpenAI JSON structure. You can enable streaming to receive tokens in real-time via Server-Sent Events. This is essential for building chat interfaces that feel responsive. Token usage metadata appears in the final chunk of the stream. This allows you to track consumption accurately without parsing every individual token.

Parameters and Configuration

Control the model's behavior using standard parameters like temperature, top_p, and stop. You can enforce JSON output using response_format for structured data generation. Function calling is supported via the tools parameter. Adjust presence_penalty and frequency_penalty to manage repetition. These settings give you precise control over the creative output.

Limits and Constraints

Each request supports a context window of 100,000 tokens combining prompt and completion. The maximum output per request is 16,000 tokens unless you set a lower limit. You are limited to 300 requests per minute and 8 concurrent requests per key. Request bodies must not exceed 8 MB. If you exceed these limits, you will receive a 429 error. Errors do not consume your credit.

Errors and Credits

Common errors include 401 for invalid keys and 402 when your prepaid credit runs out. Requests that are refused due to content policy are free. Credit never expires, so you can top up whenever needed. If you encounter a billing issue, use the Support page to resolve double charges or other anomalies. Your credit balance is always visible in your dashboard.

cURL

Copycurl https://api.bestllmfornsfw.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 parameters for my deployment config"}]
  }'

Python

Copyfrom openai import OpenAI

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