Uncensored ai API documentation

Authentication and Base URL

Your API key authenticates every request to the base URL https://api.uncensoredopensourceai.com/v1. You obtain this key instantly after signing up with Google or an email address on the Get API key page. Pass the key in the Authorization header as a Bearer token. The system rejects invalid credentials with a 401 status code. Errors and refusals during testing do not consume your prepaid credits.

First Request

Send a standard chat completion request to generate text from the model. The endpoint accepts POST requests to /v1/chat_completions with a JSON body containing your messages. You must specify the model identifier as "uncensored". This open-weight model runs on our servers and is tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor model.

Use the following curl command to send your first message:

Copycurl https://api.uncensoredopensourceai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list python stdlib modules"}]
  }'

Python SDK Integration

Use the official OpenAI Python library to interact with the API seamlessly. Set the base_url and api_key environment variables or pass them directly to the client. The client handles serialization and response parsing automatically. You can send system prompts to guide the model behavior. The library supports both synchronous and asynchronous patterns for different use cases.

Here is how to initialize the client and send a message:

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredopensourceai.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 Integration

The Node.js SDK works identically to the Python version for this uncensored AI API. Configure the base URL and API key in the initialization object. Send messages using the chat.completions.create method. The response object contains the generated text and usage statistics. You can handle errors gracefully by catching network or API exceptions. This setup allows you to integrate the model into any JavaScript or TypeScript application.

Initialize the client and make a request:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredopensourceai.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 and Tokens

Enable streaming by setting the stream parameter to true. The API returns data in Server-Sent Events (SSE) format. Each chunk contains partial text updates. The final chunk includes the total token usage for the request. This feature reduces perceived latency for long outputs. You can process tokens in real time as they are generated. The model supports a context window of 100,000 tokens for prompt and completion combined.

Example streaming request:

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

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. If you send too many requests, you receive a 429 rate limit error. A 402 error indicates insufficient prepaid credit. Top up your account with USDT on TRC20 or USDC on Base. Credits never expire and are charged only for successful token usage. The model handles long contexts efficiently up to the 100,000 token limit.