API Reference and Quickstart

Authentication and Base URL Setup

Use your API key with the base URL https://api.unlimitedaiapikey.com/v1. Send your key in the Authorization: Bearer <key> header. This setup works with any OpenAI-compatible SDK. No subscription locks apply. Your credit never expires. Errors are free. Refusals are free. Only actual tokens cost money.

Chat Completions Endpoint

Send POST requests to /v1/chat/completions. Use the model ID uncensored. The model answers without standard content refusals for lawful adult use. It is not GPT or Claude. It is an open-weight model. No embeddings or image generation exist here. Just text in, text out. Simple and direct.

Python SDK Integration

Install the official SDK. Configure the base URL and key. Use the uncensored model ID. The Python client handles retries automatically. It supports streaming. It supports JSON mode. You control the parameters. No vendor lock-in. Pure inference power. Reliable performance.

Node SDK Usage

Require the SDK package. Set the environment variables. Call the chat completions method. The Node client streams data efficiently. It parses JSON responses cleanly. You can set custom headers. The library handles the network layer. Focus on your logic. The API does the heavy lifting.

Streaming Responses and Usage

Enable streaming by setting stream: true. Receive data chunks via Server-Sent Events. Token usage appears in the last chunk. This helps you track costs in real-time. The context window is 100,000 tokens. Max output is 16,000 tokens. Monitor your rate limits closely. Adjust your batch sizes accordingly.

Error Handling and Limits

Handle 401 for invalid keys. Handle 402 when credit is low. Handle 429 for rate limits (300 req/min). The request body limit is 8 MB. You get 8 concurrent requests. One key per account. Replace the key if needed. Errors do not consume credit. Check the status codes. Fix the issue. Retry the request.

cURL

Copycurl https://api.unlimitedaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List open source alternatives to proprietary llm models"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.unlimitedaiapikey.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.js

Copyimport OpenAI from "openai";

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

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)