UncutGPT API — Models, Billing and OpenAI Compatibility

What it is

A chat completions API behind the same models the product runs, for scripts, agents and your own interface. It is OpenAI-compatible, so an existing client works by changing the base URL and the key.

• Base URL: https://uncutgpt.com/api/v1
• Shape: chat completions, as the OpenAI SDK sends them
• Auth: a bearer key made in the console, never a chat login

Billing

• Access is OpenAI-compatible: the documented base URL is /api/v1 and the documented shape is chat completions.
• Billing is prepaid credit, drawn down per token: prompt and completion tokens are counted against the model's price.
• A chat subscription does not include API credit. They are separate balances and separate purchases.
• Keys are created in the console at /api; the reference is at /docs/api.

Credit, usage per key and the prices per model are all in the console.

A first request

curl https://uncutgpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $UNCUTGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model id from the reference>",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Model ids, streaming fields and the exact request and error shapes are in the API reference.

Chat subscription versus API

They are separate purchases. A chat plan is a monthly card charge for this website’s interface; an API balance is prepaid credit drawn down per token. Paying for one does not grant the other, and limits do not carry across. See pricing.

Models

The API serves the models listed in the reference with their own prices. Which families the product carries overall, and what can change, is on the model page.

Console and reference

Create and revoke keys, watch usage and top up credit in the console. The console itself is deliberately kept out of search results; the reference at /docs/apiis the public document to work from.