Unverified50% confidenceFactExact time
When Token Pass credits for a billing period are exhausted, requests made with standard keys or OIDC tokens automatically fall back to the team's AI Gateway credits, and requests are not interrupted.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/5/2026
First Seen
Valid until: 2/3/2027
Sources
Related Entities
Related Claims
UnverifiedAfter the credit balance is used up, API requests switch to consuming the user's purchased credits or auto-recharge; when neither is available, API requests stop directly, and the subscription itself is not charged.70% similarUnverifiedToken Pass enables Zero Data Retention (ZDR) by default, requests run through the selected provider, and inference takes place in the United States and the European Union; after each request completes, AI Gateway and the provider delete the prompt and response content, and users' prompts are not used to train models.66% similarUnverifiedQuota limits can directly restrict the number of requests and token consumption per minute or per day in Vertex AI's API quota settings, establishing a ceiling at the entry point with no risk of overspending due to billing delays.66% similarUnverifiedSubscription-based AI coding tools universally impose periodic usage caps, in the form of token quotas, request counts, or credits.66% similarUnverifiedAntirion's billing model reserves a token estimate at admission and settles exactly once with actual usage at request end; when a client disconnects midway the request is not cancelled and the partial cost already generated is still charged.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1141195API
curl https://kongchang.com/api/v1/knowledge/claims/1141195MCP
get_claim(id=1141195)