An ordinary conversation queries nothing and pays for tokens only. If your question needs current information — recent news, a number that moves during the day — the data is fetched before the model answers and that message carries a R$ 0.05 access fee. When it happens, a badge appears on the reply.

Start the conversation
Write a message below. You pay only for the tokens you use — the cost of each response appears right under it.
Enter sends · Shift+Enter adds a line break

Inference usage

Amounts already calculated and charged — the same numbers that come out of your balance.

Loading usage…

Models and pricing

Price per million tokens, in Brazilian reais. You pay only for what you use — no monthly fee and no reservation.

ModelIdentifierContext Input (R$/1M)Output (R$/1M)
Loading…

How to use it in your application

The API is compatible with the OpenAI format: change the base URL and the key.

1. Generate a gpub_live_… key in the dashboard, under API Keys.
2. Point the base URL to https://gpubrasil.com.br/v1.
3. Call POST /v1/chat/completions with the model identifier (e.g. gpub-mini).
4. Usage comes out of the same balance in Brazilian reais you already use here — payment in reais via Pix, with no IOF tax and no currency conversion, and support in Portuguese.

Full reference: API documentation · model API guide.