Guides, model notes and product updates

A technical guide to cancelling queued Seedance video generation jobs on TokenLab using DELETE /v1/tasks/{id}, covering error code handling, status transitions, and billing settlement semantics.

Reusable video references work better as assets with lifecycle status. This rewrite shows how the Seedance material library handles groups, liveness checks, automatic preparation, and 409 retries.

Debug failed AI API calls in the TokenLab Request Console. Inspect request IDs, status, cache state, model context, key source, and redacted payload previews from one dashboard.

Check your TokenLab workspace balance, total top-ups, and total spend programmatically using the Management API GET /v1/management/balance endpoint and management tokens.

TokenLab usage exports now let finance and engineering teams pull matching usage records directly from the dashboard, so spend reviews start with real records instead of guesswork.

TokenLab determines payload schemas by native endpoint selection rather than dynamic format hint headers. Learn how to configure documented headers for billing reconciliation, rate limiting, and task tracking.