Uncensored.com: Quickstart your uncensored ai integration

Prerequisites: installing the official SDK

Install the client library your language supports. We rely on the standard OpenAI SDKs because they handle retries and streaming for you. Our API accepts any client that speaks the OpenAI protocol.

For Python users, run pip install openai. Node developers should use npm install openai. These libraries abstract the HTTP details so you can focus on prompts. Keep your dependencies updated to avoid compatibility issues with newer API features.

Configuration: setting your base_url and api_key

Point your SDK client to our specific base URL and provide your API key. This configuration ensures your requests reach our uncensored model instead of OpenAI’s servers.

Set the base URL to https://api.uncensoredcom.com/v1. Use the key you generated when you signed up via Google or email. Do not use sk-... keys from other providers. Our service is independent and does not route through OpenAI.

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

Basic request: sending a simple chat completion

Send a POST request to /v1/chat/completions with your prompt and the model ID uncensored. The API returns text output directly. No embeddings or image generation are available in this endpoint.

Copycurl https://api.uncensoredcom.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check if the server is online and responding correctly"}]
  }'

Advanced features: streaming, JSON mode, and function calling

Enable streaming by setting stream: true to receive tokens as they generate. Use response_format: {type: "json_object"} for structured data. Function calling works via the standard tools parameter. These features allow you to build complex applications without parsing raw text.

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 and errors: understanding your quota

Respect the 300 requests per minute limit and the 8 concurrent request cap per key. Errors like 401 indicate an invalid key, while 402 means you need to top up with crypto. A 429 error signals you have hit the rate limit.

Your context window is 100,000 tokens total. If you exceed this, the model will drop older tokens. Requests under 8 MB are processed normally. Errors and refusals do not consume your token credit.

Token usage: reading the response headers

Check the response headers to see exactly how many tokens you used. This transparency ensures you only pay for what you consume. Our prepaid credit model means errors are free, so you can test freely.

Monitor your usage to avoid running out of credits unexpectedly. Top up with USDT or USDC to keep your integration running smoothly. Credit never expires, so you can pause and resume at your own pace.