Quickstart: Integrate the uncensored llm api

Prerequisites: SDK and API Key

Install your preferred SDK and create a key in seconds. Sign up with Google or email to get a key immediately. No phone number required. The key authenticates all requests to the base URL. You start with $0.50 trial credit. It lasts for seven days. Errors consume no tokens. You can top up later with crypto.

Base URL: HTTPS://api.uncensoredllmsonline.com/v1

Model ID: uncensored

Copycurl https://api.uncensoredllmsonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all required dependencies for a node project"}]
  }'

Basic Text Completion Request

Send a standard chat completion request. The API accepts the same JSON structure as OpenAI. Set the model to uncensored. Pass your system and user messages. The response returns generated text. You pay only for tokens used. Input costs $0.15 per 1M tokens. Output costs $0.50 per 1M tokens. Refusals are free. This uncensored LLM API handles any topic. It does not block creative or adult content.

Streaming Responses with SSE

Enable streaming for lower latency. Set the stream parameter to true. The API returns a Server-Sent Events stream. Receive tokens as they generate. This is ideal for chat interfaces. The final chunk contains usage statistics. You can update the UI in real time. The uncensored API supports full SDK compatibility. Streaming works with any OpenAI-compatible client.

Copyfrom openai import OpenAI

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

Enforcing JSON Mode

Force structured output for reliable parsing. Use response_format with {"type": "json_object"}. The model guarantees valid JSON. This works with the uncensored AI API. You can define schemas in your system prompt. The API returns parsed data. Use this for data extraction or tool inputs. JSON mode is stable and fast. It works with the 100,000 token context window.

Copyimport OpenAI from "openai";

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

Function Calling (Tools)

Define tools for the model to call. Pass a list of function definitions. The model decides when to use a tool. It returns arguments in JSON format. You execute the function and feed the result back. This enables complex workflows. The uncensored model supports tool calling. It follows instructions accurately. Use this for agents or automation. The API handles tool choice automatically.

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)

Managing Context and Tokens

The context window is 100,000 tokens. This includes prompt and completion. Max output is 16,000 tokens. Set max_tokens to control length. Default is 2,048 tokens. Request limits are 300 per minute. Concurrent requests are limited to 8. Request body maxes at 8 MB. Errors return standard HTTP codes. 401 means invalid key. 402 means no credit. 429 means rate limit. Credit never expires. You pay for real usage.