API documentation

Base URL and authentication

Direct your requests to https://api.aiuncensy.com/v1 and pass your key in the standard header. This base URL works with any OpenAI-compatible client without custom adapters. Retrieve your key immediately after signing up with Google or email. The key identifies your prepaid balance and enforces your rate limits. Keep it secure because errors do not consume credit, but lost keys require regeneration.

Make your first request

Send a POST request to /v1/chat/completions with your model ID and prompt. The system returns a direct text response for any lawful topic. Use the model ID uncensored to access the uncensored AI model optimized for long context. Your request body must stay under 8 MB. Errors like invalid keys or empty responses do not charge your tokens.

Python SDK integration

Initialize the client with your base URL and key to start chatting. The Python SDK handles tokenization and retries automatically. Set the model to uncensored for consistent output. You can adjust temperature and top_p to control creativity. This approach works for simple scripts or complex application backends.

Node SDK integration

Configure the Node client to point at our API endpoint. Pass your credentials and the model ID uncensored. The library manages the HTTP connection and response parsing. You can stream data or wait for the full completion. This method fits well in serverless functions or Express apps.

Streaming responses

Enable streaming by setting the stream parameter to true. You receive a sequence of chunks instead of one large payload. The final chunk contains the total token usage for accurate billing. This feature reduces perceived latency for long outputs. Monitor the stream to handle partial responses gracefully.

Rate limits and constraints

Each API key supports 300 requests per minute and 8 concurrent connections. If you exceed these limits, the system returns a 429 error. A 401 error means your key is invalid. A 402 error indicates you need to top up your crypto credit. The context window holds 100,000 tokens total, with a max output of 16,000 tokens.

cURL

Copycurl https://api.aiuncensy.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top 5 rust async crates for web servers"}]
  }'

Python

Copyfrom openai import OpenAI

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