Uncensored LLM API Documentation

Authentication & Base URL

The API key authenticates every request to our hosted endpoint. Generate your key via Continue with Google or email on the dashboard page. Pass this key in the Authorization header using the Bearer scheme.

• Base URL: https://api.unrestrictedartificialintelligence.com/v1
• Header: Authorization: Bearer YOUR_API_KEY

Each account supports one active key; generating a new one invalidates the previous key immediately. No phone number verification is required during signup.

Chat Completions Endpoint

Send text prompts to the /v1/chat/completions endpoint to receive generated responses. This endpoint handles all standard chat interactions without complex routing logic.

Specify the model ID as uncensored in the request body. The API returns text output directly, supporting both synchronous and asynchronous workflows.

Errors like insufficient credit return a 402 status, while invalid keys trigger a 401 response. No hidden fees apply to failed requests.

Copycurl https://api.unrestrictedartificialintelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current UTC timestamp"}]
  }'

Python SDK

Integrate the API into Python applications using the official OpenAI SDK. Configure the client with the custom base URL and your API key to ensure requests route correctly to our servers.

Set the model parameter to uncensored to access the unrestricted model. This approach allows you to leverage existing SDK features like retries and error handling.

Copyfrom openai import OpenAI

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

Use the Node.js SDK to build backend services that require high-throughput text generation. Initialize the client with the specific base URL to avoid routing conflicts with standard OpenAI endpoints.

Define the model as uncensored to ensure the response aligns with the unrestricted behavior. The SDK handles JSON serialization and network requests automatically.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.unrestrictedartificialintelligence.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 & SSE Support

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream, allowing you to process tokens as they are generated.

Token usage statistics are included in the final chunk of the stream. This reduces perceived latency for large responses while maintaining full control over the output flow.

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

The context window supports 100,000 tokens for combined input and output. Max output per request is 16,000 tokens, or 2,048 tokens if max_tokens is unspecified.

Rate limits enforce 300 requests per minute and 8 concurrent requests per key. Request bodies must not exceed 8 MB. These limits ensure stable performance for scalable deployments.