Uncensored AI API Quickstart

Prerequisites and base URL

Your API key authenticates every request to the base URL https://api.uncensoredaidownload.com/v1. This endpoint works with standard OpenAI SDKs. You only need to change the base_url variable in your client configuration. No complex routing or multi-model selection is required. Simply point your existing infrastructure at this single, raw uncensored model.

Authentication and key management

Pass your API key in the Authorization header. Use the format Bearer YOUR_API_KEY. Each account supports one active key at a time. Generating a new key immediately invalidates the previous one. This keeps your integration secure without managing multiple credentials. Sign up via Google or email to receive your key instantly.

Basic chat completion example

Send a POST request to /v1/chat/completions with your messages. The model id is always uncensored. We charge strictly by real token usage. Errors and refusals are free. This approach ensures you only pay for actual content generation without hidden fees for throttled keys.

Streaming responses with SSE

Enable streaming by setting stream to true. You receive Server-Sent Events (SSE) for real-time token delivery. The final chunk contains the total token usage statistics. This method reduces perceived latency for long outputs. It is ideal for chat interfaces that need instant feedback.

Function calling and tools

Define tools in your request to enable function calling. Use tool_choice to control execution. The model supports structured tool definitions. This allows your application to parse responses dynamically. Pass the function name and arguments in the tool calls.

JSON mode and parameters

Force structured output by setting response_format to {"type": "json_object"}. You can adjust temperature, top_p, and stop sequences. The context window supports 100,000 tokens total. Max output is 16,000 tokens per request. These parameters give you precise control over generation quality.

cURL

Copycurl https://api.uncensoredaidownload.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the latest version of the release notes"}]
  }'

Python

Copyfrom openai import OpenAI

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