API Documentation

Authentication and Base URL

Start by retrieving your API key from the dashboard. Use the base URL https://api.bestuncensoredaimodels.com/v1 and include your key in the Authorization header. This endpoint works with any OpenAI-compatible client, ensuring you can swap libraries without changing your infrastructure.

• Key format: Bearer YOUR_API_KEY
• No phone number required for signup.
• One active key per account.

First Request

Send a simple chat completion to verify connectivity. The model ID is uncensored. This request demonstrates the standard text-in, text-out interaction without guardrail refusals.

This is a focused inference server. You get direct access to the model without intermediate routing layers that might alter your prompt.

Copycurl https://api.bestuncensoredaimodels.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate the user guide for this new API endpoint"}]
  }'

Python SDK

Integrate the API into your Python scripts using the official SDK. Set the base URL to point to our hosted endpoint. This allows you to leverage existing tooling while accessing an uncensored model for your specific use case.

Configure your client with the API key and the correct base URL. The response object provides standard fields for tokens and content.

Copyfrom openai import OpenAI

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

Use the Node.js SDK for server-side automation. Pass the base URL and API key to initialize the client. This approach is ideal for backend services generating content at scale.

The SDK handles serialization and error parsing. You receive structured data that fits into your existing data pipelines.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.bestuncensoredaimodels.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 and Token Usage

Enable streaming via Server-Sent Events (SSE) for lower latency. Token usage statistics appear in the final chunk of the stream. This method reduces perceived wait times for long-form generation tasks.

Monitor the stream to handle partial outputs gracefully. The API returns real-time data as it generates, allowing immediate processing of initial tokens.

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)

Limits, Errors, and Context

Your account supports 300 requests per minute and 8 concurrent requests per key. The context window holds 100,000 tokens total, with a max output of 16,000 tokens per request. Errors like 401 (invalid key) or 402 (no credit) do not consume your prepaid balance. Refusals for minor-related content are free. Request bodies must stay under 8 MB. Errors and refusals are free.