Open Usage in the console to see your plan, current period, and remaining request and token allowances. New accounts start with a free plan — the default monthly allowance is 1,000 recorded requests and 2 million tokens.
API calls, playground runs, and test-key requests share the same account allowance. Requests that reach inference can count even when they fail.
When you reach a limit
A quota rejection returns 402. Token use is measured after a request finishes, so the last accepted request can take you past the token allowance. Later requests are blocked.
Only one request can run at a time per account. Overlapping requests return 429; wait before retrying.
Costs
Any cost estimate shown in the console is an estimate of token overage — it is not an invoice. Self-service checkout, top-ups, and payment collection are not available.