Quickstart: Integrate the uncensored AI API

Prerequisites: Install the SDK

Start by installing the official SDK for your preferred language. Our API works with any standard OpenAI-compatible client. You only need a base URL and an API key. Create an account to get your key instantly. It is shown once after signup. Keep it secure. No phone number is required. Just use email or Google.

Initialize the client

Point your client to our specific base URL. This ensures you hit the uncensored endpoint directly. Do not use the default OpenAI URL. Replace the placeholder key with yours from the dashboard. The model ID is simply "uncensored". This setup eliminates proxy layers. You get direct access to the abliterated model. Configuration is minimal. Just set the base URL and key.

Send your first chat completion

Send a simple request to generate text. The API accepts standard chat formats. You can specify temperature and top_p for control. Our model answers without refusing lawful adult content. Errors and refusals are free. Only real usage counts. The context window is 100,000 tokens. Output is capped at 16,000 tokens. Use the code below to start.

Enable streaming for real-time responses

Streaming is essential for chat interfaces. Enable it by setting stream to true. The API returns tokens as they are generated. This reduces perceived latency significantly. You get token usage in the final chunk. This helps track costs accurately. Streaming works with all parameters. It is the recommended mode for users. See the example below.

Handle function calling and JSON mode

Our API supports tools and JSON mode. Define functions in your request. The model returns structured data. Use response_format for strict JSON output. This is vital for integrations. You can also set tool_choice. Parameters like seed ensure reproducibility. Presence and frequency penalties help control repetition. The API handles the rest. No extra configuration is needed. Use this for reliable data extraction.

Check your usage and balance

Monitor your account directly in the dashboard. Credit is prepaid and never expires. Errors do not consume tokens. Limits are 300 requests per minute. You can have 8 concurrent requests. Request bodies are capped at 8 MB. One key per account. If you get a 401, check your key. A 402 means no credit. A 429 means rate limit. Top up with crypto for bonuses.

cURL

Copycurl https://api.uncensoredaimodeldownload.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set system temperature to 1.5 for creative output."}]
  }'

Python

Copyfrom openai import OpenAI

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