API Documentation for uncensored AI

Base URL and Authentication

Point your client at https://api.aiunlimited.cc/v1 and include your API key in the header. We issue one key per account that grants full access to the endpoints. Authorization relies on a standard Bearer token scheme that works with any OpenAI-compatible SDK.

Copycurl https://api.aiunlimited.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List three reasons why open source models beat closed APIs"}]
  }'

Keep the key secure because it controls your prepaid credit. You can generate a new key from the dashboard if needed, and the old one stops working immediately.

First Request with uncensored AI

Send a POST request to /v1/chat/completions with the model ID set to uncensored. This endpoint accepts standard message arrays and returns text responses without content filters. Use this structure to test connectivity and verify token counting.

Copyfrom openai import OpenAI

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

The response includes usage statistics so you can track costs accurately. Debugging is straightforward because errors return standard HTTP codes with clear JSON messages.

Node.js Integration for Agents

Initialize the client with your base URL and key to integrate with existing Node.js workflows. This setup supports both synchronous calls and async patterns for building agents. Configure the client once and reuse it across multiple requests.

Copyimport OpenAI from "openai";

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

Pass the uncensored model ID to ensure you get the unrestricted output. The library handles connection pooling and retry logic automatically.

Streaming Responses

Enable streaming by setting stream: true in your request parameters. This mode sends chunks as they are generated, reducing perceived latency for long outputs. You must handle the final chunk carefully to extract total token usage.

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)

The last chunk contains a usage object with input and output token counts. Parse this data to update your local credit balance accurately.

Rate Limits and Errors

Expect a 429 status code when you exceed 300 requests per minute or 8 concurrent connections per key. A 401 error indicates an invalid or expired API key, while 402 means your prepaid credit is insufficient. Request bodies cannot exceed 8 MB in size.

Implement exponential backoff for 429 errors to avoid overwhelming the server. Check your account balance regularly since errors do not consume tokens.

Context Window and Constraints

The model supports a 100,000 token context window combining prompt and completion. Max output per request is 16,000 tokens unless you specify a lower max_tokens value. Default output reverts to 2,048 tokens if unspecified.

Monitor your token usage closely because costs scale with length. Use the stream option to manage memory efficiently during long conversations.