Integrate the Uncensored AI in Minutes

Install the Standard OpenAI SDK

Start by installing the official client library for your preferred language. This ensures you use the exact same request structures as major providers while we handle the uncensored backend. No custom wrappers or legacy HTTP calls are required. You can proceed with pip or npm depending on your environment.

Configure Base URL and API Key

Point your client to our endpoint to route requests correctly. You must set the base URL to HTTPS://api.aiuncensoredthe.com/v1 and provide your key from the dashboard. This configuration ensures all calls hit the uncensored LLM API instead of the default OpenAI servers.

• Base URL: HTTPS://api.aiuncensoredthe.com/v1
• Model ID: uncensored
• Auth: Bearer token via API key

Send Your First Chat Completion

Make a standard POST request to /v1/chat/completions with your prompt. The uncensored AI API responds with text without applying standard content filters. You can send any topic, including adult or controversial subjects, as long as it does not involve minors. The response returns immediately with the generated token stream.

Copycurl https://api.aiuncensoredthe.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return current UTC timestamp in ISO format"}]
  }'

Enable Streaming for Real-Time Output

Set the stream parameter to true for lower latency perception. This sends tokens one by one via Server-Sent Events (SSE). You can display output instantly while the model continues generating. The uncensored models handle high-throughput streams efficiently without dropping connections. This approach reduces perceived wait times significantly.

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)

Use Tool Calling and JSON Mode

Activate function calling to let the model execute external logic. Pass a tools array with your schema definitions in the request body. The API respects tool_choice parameters for precise control. You can also force JSON output using response_format json_object for structured data extraction. This flexibility supports complex integration patterns.

Copyfrom openai import OpenAI

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

Manage Context and Parameters

Our uncensored AI supports a 100,000 token context window for prompt and completion combined. Max output is 16,000 tokens per request, or 2,048 if unspecified. You can adjust temperature and top_p for creativity. Rate limits are 300 requests per minute per key. Errors like 401 indicate invalid keys, 402 means no credit, and 429 signals rate limiting.

Copyimport OpenAI from "openai";

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