Uncutly AI API Documentation

First Request

Send your first message to the /v1/chat/completions endpoint using your preferred HTTP client.

The model identifier is simply uncensored. This open-weight model runs on our servers and answers without typical content refusals for lawful adult use.

You can send standard prompt structures. The API accepts text input and returns text output. It is compatible with any OpenAI SDK or client that supports the chat-completions format.

Here is a basic example using cURL to get a response.

Copycurl https://api.uncutlyai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Show me the API endpoint for text generation"}]
  }'

Python SDK

Use the official OpenAI Python package to interact with our API with minimal code.

Set the base_url and api_key parameters in your client initialization. This ensures requests route to our uncensored endpoint instead of OpenAI's servers.

The model name is uncensored. You can pass messages as a list of dictionaries. The response object contains the generated text in response.choices[0].message.content.

This approach works for simple scripts or complex application logic. It handles serialization automatically.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncutlyai.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

Integrate the API into your Node.js applications using the openai package.

Configure the client with our base URL and your API key. The SDK handles the HTTP requests and parses the JSON response.

Call the chat.completions.create method with the model uncensored. You can define system prompts or user messages as needed.

This method is reliable for server-side generation. It fits well into Express routes or background jobs.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncutlyai.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

Receive text token-by-token using Server-Sent Events (SSE) for lower perceived latency.

Set the stream parameter to true in your request. The API returns a stream of chunks instead of a single full response.

Each chunk contains partial text. You can concatenate these chunks to build the final message. This is useful for chat interfaces that update in real time.

The last chunk includes usage statistics. You can track token consumption directly from the stream.

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 & Context

Understand the constraints and error codes to debug your integration quickly.

Your context window is 100,000 tokens total. This includes both the input prompt and the generated output. You can set a maximum output of 16,000 tokens per request.

Rate limits are set to 300 requests per minute per key. You can run 8 concurrent requests simultaneously. The request body limit is 8 MB.

Common errors include 401 for an invalid key and 402 when you run out of prepaid credit. A 429 error means you hit the rate limit. Errors do not consume your credit balance.

Pricing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Credit is prepaid and never expires.