API Documentation & Quickstart

Authentication

Use your API key in the Authorization header. Get one instantly via Google or email on the key page. No phone number required.

• Header: Authorization: Bearer YOUR_API_KEY
• Header: Content-Type: application/json

Keys are single-use per account. Replace old keys immediately.

Chat Completions Endpoint

Send messages to POST /v1/chat/completions. The model ID is uncensored. Context window is 100,000 tokens.

Base URL: https://api.unlimitedtokenai.com/v1. Errors and refusals are free.

Copycurl https://api.unlimitedtokenai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check my python syntax for errors"}]
  }'

Parameters: Temperature, Top P, and More

Control creativity with temperature and top_p. Use stop sequences and seed for reproducibility. Set max_tokens to limit output; default is 2,048.

Supports presence_penalty and frequency_penalty. No fine-tuning or embeddings.

Copyfrom openai import OpenAI

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

Streaming Responses

Enable streaming with stream: true. Receive server-sent events (SSE). Token usage appears in the final chunk.

Handle partial tokens carefully. Ideal for real-time chat interfaces.

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)

Function Calling

Define tools in tools. Set tool_choice to auto or specific names. Response format includes tool calls.

Use JSON mode with response_format: {"type": "json_object"} for structured data.

Copyimport OpenAI from "openai";

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

Limits, Errors, and Context

Rate limit: 300 requests per minute. Concurrent: 8 requests. Body size: 8 MB. Error 401 means invalid key. 402 means no credit. 429 means rate limit exceeded.

Context window is 100,000 tokens total. No SLA or certifications. Crypto top-up only.