Quickstart guide for uncensored ai

Install the standard OpenAI SDK

Start by installing the official library for your preferred language. Our interface is fully compatible with standard tools, so you do not need a custom client. Use pip for Python or npm for Node.js to add the dependency to your project. This ensures you can leverage existing code patterns without learning a new protocol.

Configure your base URL and API key

Point your SDK client to our dedicated endpoint instead of the default provider. You must set the base URL to HTTPS://api.aiopenuncensored.com/v1 and provide your unique API key. This configuration directs traffic to our uncensored model server rather than the commercial giant. Your key is generated instantly upon signup, so you can begin testing right away.

Send your first chat completion request

Make a POST request to /v1/chat/completions with the model identifier "uncensored". This simple call returns raw text without the usual content filters blocking your input. You can send standard messages and receive direct responses. Check the code below for the exact curl command to verify connectivity.

Handle streaming responses and token usage

Enable streaming by setting the stream parameter to true. The API returns chunks as they are generated, allowing you to display text in real time. The final chunk contains the complete token usage statistics for billing and monitoring. This approach reduces perceived latency for your end users significantly.

Implement function calling and JSON mode

Use the tools parameter to define functions your model can call. You can also enforce strict JSON output by setting response_format to json_object. This ensures your application receives structured data without parsing errors. The model supports tool_choice and other standard parameters for precise control.

Understand rate limits and token constraints

Your API key allows 300 requests per minute and supports up to 8 concurrent requests. The context window holds 100,000 tokens total, with a maximum output of 16,000 tokens per request. Errors like 401 or 429 are common and indicate you should check your key or wait briefly. Credit is only consumed for successful token usage.

cURL

Copycurl https://api.aiopenuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check if port 8080 is open"}]
  }'

Python

Copyfrom openai import OpenAI

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