API Documentation & Quickstart Guide

Base URL and Authentication Setup

The API endpoint is HTTPS://api.unrestrictedaitools.com/v1. Use the standard OpenAI SDKs by changing the base_url and providing your API key. You can sign up with Google or email to get your key instantly.

Copycurl https://api.unrestrictedaitools.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of france"}]
  }'

Every request must include the Authorization header. Your key grants access to the uncensored model without extra configuration steps.

First Request: POST /v1/chat/completions

Send a POST request to /v1/chat/completions with your messages. The model ID is 'uncensored'. Input is text, output is text. No embeddings or image generation here.

Copyfrom openai import OpenAI

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

Keep your prompts simple. The API handles the rest. Errors are free, so you can test freely.

Streaming Responses and Token Usage

Enable streaming by setting stream to true. Receive tokens via SSE. The last chunk contains total token usage. This helps you track costs in real-time.

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)

Streaming reduces perceived latency. Use it for long responses or interactive apps. Always check the final chunk for accurate counts.

Parameters: Temperature, Top-P, and Stop

Adjust temperature for creativity. Set top_p for nucleus sampling. Use stop sequences to halt output. These parameters give you control over the generation style.

Copyimport OpenAI from "openai";

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

Higher temperatures produce more varied text. Lower values are more deterministic. Experiment to find the right balance for your use case.

JSON Mode and Function Calling

Use response_format json_object for structured output. Enable function calling with tools and tool_choice. This allows the model to execute actions or return data in a specific format.

Define your tools clearly. The model will follow the schema. This is useful for building agents or data extraction pipelines.

Rate Limits and Context Window

You get 300 requests per minute and 8 concurrent requests. The context window is 100,000 tokens. Max output is 16,000 tokens. Request bodies must be under 8 MB.

If you hit a 429, wait a moment. A 401 means invalid key. A 402 means no credit. These limits ensure fair usage for all developers.