OpenAI-compatible uncensored LLM API

Base URL and authentication

Start by pointing your client to our base URL. The endpoint is https://api.uncensoredapikey.com/v1. Pass your API key in the standard Authorization header. This works with any OpenAI-compatible client. You get a key instantly after signup. No phone number required. Just Google or email login.

First request

Send a standard chat completion request. Use the model ID uncensored. The API responds with text output. Here is a basic cURL example.

Copycurl https://api.uncensoredapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check api key status"}]
  }'

This confirms your key works. You are ready for more complex prompts. The model handles context up to 100,000 tokens. Input and output count toward this limit. Keep your payloads under 8 MB.

Python SDK integration

Use the official OpenAI Python library. Set the base URL to ours. Pass your key as the API key. This keeps your existing code intact. You just swap the endpoint.

Copyfrom openai import OpenAI

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

Run this locally. It connects to our servers. You pay only for tokens used. Errors do not charge credit. This makes testing cheap. Try different temperatures. Adjust top_p for creativity.

Node.js SDK setup

Initialize the OpenAI Node client. Configure the base URL. Set the API key. This works for browser or server side. It fits into any Express or Next.js app.

Copyimport OpenAI from "openai";

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

Handle the response stream. Or use async/await. The model responds fast. No waiting for embeddings. No waiting for images. Just text. This speed matters for roleplay. It matters for data processing. Keep the code simple.

Streaming responses

Enable streaming by setting stream: true. The API sends Server-Sent Events. Each chunk contains partial text. The last chunk has token usage. This is crucial for long sessions. You see tokens grow in real time.

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)

Display tokens as they arrive. This improves UX. Users feel the AI is alive. Do not buffer the whole response. Stream it directly to the UI. It reduces latency perception. Your app feels responsive.

Limits, errors and context

Watch your rate limits. You get 300 requests per minute. Only 8 concurrent requests per key. If you hit 429, wait a moment. A 401 means bad key. A 402 means low credit. Top up with crypto. USDT or USDC only. Minimum $20. Bonus credit applies. Your context window is 100k tokens. Output max is 16k tokens. Set max_tokens wisely. Refusals are free. Errors are free. Only use tokens count.