Models & pricing

Pay per token in EUR. Prices are per 1 million tokens and apply from the next request after any change.

How billing works

Each request costs (input tokens × input price + output tokens × output price) ÷ 1,000,000.
Before a request starts we reserve its maximum possible cost from your balance. When it finishes you're charged the actual cost and the rest is released right away.
If your balance can't cover the reservation, the request is rejected with 402 and nothing is charged. Set max_tokens to keep reservations small.

How much does it cost?

Each model has a price per 1M input tokens and per 1M output tokens in EUR. You pay only for what you use; see the pricing page.

How do I top up?

Open Billing in the dashboard and pay by card. The minimum top-up is €5 and the maximum is €1,000 per payment.

What happens when my balance runs out?

Requests whose maximum cost can't be covered are rejected with 402 insufficient_balance. Your balance never goes negative.

Why was more reserved than I was charged?

We reserve the maximum possible cost before each request and release the unused part as soon as it finishes. Set max_tokens to reduce reservations.

Create an account, top up from €5 and make your first request.