Uncensored API Quickstart

Base URL and authentication

Your API key authenticates every request to the base URL https://api.unhingedaichatbot.com/v1. Use this endpoint with any standard OpenAI SDK or compatible HTTP client. Top-ups are crypto only, accepting USDT on the TRC20 network or USDC on Base. The minimum top-up amount is $20, and the maximum is $500. Your prepaid credit never expires, so you can pause usage without losing funds. Errors and refusals consume zero tokens, meaning you only pay for successful completions.

Sending your first request

Make a POST request to /v1/chat/completions with the model ID uncensored. The model is an open-weight LLM tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, or Llama. You receive raw text output without the overhead of enterprise subscriptions. Set your temperature and top_p parameters to control creativity. The context window supports 100,000 tokens for both prompt and completion combined. Max output per request is 16,000 tokens unless you specify a lower limit.

Streaming responses with SSE

Enable streaming by setting stream: true in your request body. The API returns Server-Sent Events (SSE) chunks containing incremental text. The final chunk includes token usage statistics for billing transparency. This approach reduces perceived latency for long-form roleplay or data extraction tasks. You can parse partial tokens in real-time without waiting for the full completion. Function calling and JSON mode also support streaming. Use this method to keep your UI responsive during heavy generation loads.

Function calling and JSON mode

Supports structured output via response_format: {"type": "json_object"} for deterministic data extraction. You can also use function calling tools with tools and tool_choice parameters. The model handles tool definitions and argument parsing without external routing. This feature works well for parsing unstructured text into structured formats. Set the seed parameter for reproducible results during development. Use stop sequences to truncate output at specific markers. These features integrate directly into the standard chat-completions endpoint.

Handling errors and limits

The API enforces a rate limit of 300 requests per minute per key. You can have up to 8 concurrent requests active simultaneously. Each request body must not exceed 8 MB. A 401 error indicates an invalid API key; regenerate it via the dashboard. A 402 error means your prepaid credit is exhausted; top up with crypto to resume. A 429 error signals you have hit the rate limit; wait briefly before retrying. Refusals for minor sexual content are free. No other charges apply for failed requests. Your key is unique per account.

SDK compatibility examples

Use the official OpenAI SDKs or any compatible client library. Change the base URL to point to our endpoint. Pass your API key in the authorization header. The model ID is always uncensored. No embeddings, images, audio, or video generation are supported. Fine-tuning and model routing are not offered. This is a single-model API designed for simplicity. You get raw text in, raw text out. Integrate it into your existing workflow with minimal code changes. The SDK handles serialization and retries automatically.

cURL

Copycurl https://api.unhingedaichatbot.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list 3 common linux kernel panic errors"}]
  }'

Python

Copyfrom openai import OpenAI

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