Quickstart Guide

Installation and setup

Connect your application to our API by updating the base URL in your client configuration.

• Base URL: https://api.modelsaiunfiltered.com/v1
• Model ID: uncensored

This endpoint works with standard OpenAI SDKs. You only need to change the base URL and provide your API key. The service is strictly for text generation via the chat-completions endpoint.

Authentication with your API key

Pass your API key in the Authorization header to access the uncensored model.

Generate a key via the dashboard using Google or email. Include Authorization: Bearer YOUR_API_KEY in every request. Keys are tied to your account balance and usage limits.

Making your first request

Send a simple message to verify the connection and receive an uncensored response.

Use the standard chat-completions structure. The model ignores typical content filters for lawful adult or controversial topics.

Copycurl https://api.modelsaiunfiltered.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a 200 word description of a medieval torture device."}]
  }'

This returns a direct answer without the usual refusal preamble.

Understanding parameters and streaming

Control creativity and response format using standard parameters like temperature and top_p.

Enable streaming to receive tokens in real-time via Server-Sent Events. This is essential for chat interfaces. The final chunk includes total token usage for billing.

Copyfrom openai import OpenAI

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

Adjust max_tokens to limit output length, defaulting to 2,048 if unset.

Node.js integration

Integrate with JavaScript environments using the official SDK.

Set the base URL and model ID in your client initialization. This ensures compatibility with existing Node.js applications.

Copyimport OpenAI from "openai";

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

The SDK handles serialization and streaming automatically. You can also use JSON mode for structured outputs.

Handling errors and usage

Monitor responses for standard HTTP status codes to manage your integration.

• 401: Invalid or missing API key.
• 402: Insufficient prepaid credit.
• 429: Rate limit exceeded (300 requests/minute).

The context window is 100,000 tokens total. Errors and refusals are free. Pay only for successful token generation.

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)