Uncensored ai API quickstart

Quick install and base URL

Start using the uncensored AI API by pointing your client to our dedicated endpoint. The base URL is https://api.uncensoredllmmodel.com/v1. This standard path works with any OpenAI-compatible SDK or HTTP client. You do not need complex routing logic. Our service delivers a single model response every time. There is no variability in model selection. The endpoint handles text completion requests efficiently. You can begin integration immediately after obtaining your key.

Authentication and API keys

Authentication requires a single API key passed in the header. Generate your key by clicking "Get API key" on the dashboard. You can sign in with Google or use an email and password. The key appears instantly on the screen. Copy it carefully before leaving the page. Use this key in every request. The system rejects requests without valid credentials. A single key is active per account. You can replace it anytime if needed.

Chat completions endpoint

Send text to the model via the chat completions endpoint. The model ID is "uncensored". It processes your input and returns unrestricted text. You can request JSON mode or function calling. Streaming is available for real-time token delivery. The context window supports up to 100,000 tokens. Output limits vary based on your configuration. Errors and refusals do not consume credit. This approach ensures consistent uncensored behavior across all requests.

Streaming and token usage

Enable streaming to receive tokens as they generate. This reduces perceived latency for long responses. The final chunk contains the complete token usage statistics. You can parse this data to track costs accurately. Streaming works seamlessly with standard HTTP libraries. It handles interruptions gracefully. The API returns standard SSE format. This method is ideal for chat interfaces. You get immediate feedback without waiting for the full response.

JSON mode and function calling

Use JSON mode to force structured output. Set response_format to json_object. The model will return valid JSON data. This is useful for parsing complex information. Function calling allows the model to invoke tools. Define your tools in the request body. The model decides when to call them. This enables complex workflows with external systems. Both features work within the standard chat endpoint.

Rate limits and error handling

Respect the rate limits to avoid interruptions. You are allowed 300 requests per minute. Concurrent requests are limited to eight per key. Request bodies must stay under 8 MB. A 401 error means your key is invalid. A 402 error indicates insufficient credit. You can top up with crypto at any time. A 429 error signals you hit the rate limit. Wait a moment before retrying. The API provides clear error messages for debugging.

cURL

Copycurl https://api.uncensoredllmmodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "set timeout to five seconds"}]
  }'

Python

Copyfrom openai import OpenAI

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