API Documentation

Base URL and authentication

The uncensored llm API uses standard OpenAI-compatible headers. Send your Authorization header with the Bearer scheme and your unique API key. This key is generated immediately after signup via Google or email. Use the base URL https://api.uncensorllm.com/v1 for all requests. Your key grants access to the uncensored model without subscription fees.

Make your first request

Send a POST request to /v1/chat/completions with your desired model and prompt. The model ID is uncensored. The system processes text input and returns text output. Errors do not consume credit. Refusals for lawful adult content are rare. Use this cURL command to test connectivity.

Copycurl https://api.uncensorllm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the area of a circle with radius 5"}]
  }'

This call verifies your authentication and returns the first tokens from the model. Check the response status code to confirm success.

Python SDK integration

Use the official OpenAI Python library to interact with our API. Set the base_url to our endpoint and provide your API key. The client handles streaming and parsing automatically. This approach works for most standard applications requiring unfiltered responses.

Copyfrom openai import OpenAI

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

Import the necessary modules and initialize the client. Pass your prompt as a list of messages. The response object contains the generated text in the choices array.

Node.js client setup

Integrate the API into your Node.js projects using the standard SDK. Configure the base URL to point to our servers. This ensures compatibility with existing codebases designed for OpenAI. You can switch providers by changing only the base URL.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensorllm.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);

Install the openai package. Create a new client instance with your credentials. Call the chat.completions.create method with your messages. Handle the response data to display or process the output.

Streaming responses

Enable streaming by setting stream to true. The API returns chunks of tokens as they are generated. This reduces perceived latency for end-users. Each chunk includes partial text and usage statistics in the final event.

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)

Process each chunk as it arrives. Accumulate the text content to form the complete response. This method is ideal for chat interfaces where immediate feedback is crucial. Monitor the done event to know when generation completes.

Limits, errors, and context

Your account has a limit of 300 requests per minute. The context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Errors return specific HTTP codes. A 401 error means your key is invalid. A 402 error indicates insufficient credit. A 429 error signals rate limiting. Prepaid credit never expires. Errors are free. Refine your prompts to stay within the 8 MB body limit.