Azure B-series credits + bursty AI workloads
Sizing a small always-on VM that occasionally needs to run a heavy bursty job like speech-to-text transcription
Azure B-series burstable VMs have a hard credit cap (e.g. B2pls_v2 maxes at 864 CPU credits, earning ~36 credit-minutes/hour at the 30% baseline per vCPU). 864 credits at full 2-vCPU burst = ~10 hours of sustained 100% CPU before throttling kicks in. Event-driven self-hosted services (Matrix synapse, Postgres, reverse proxy, etc.) bank credits 24/7 because they idle at <1% CPU between requests — meaning a tiny B-series box can pay for a multi-hour transcription run effectively for free, as long as you arent doing it daily. Check via az monitor metrics list --metric CPU Credits Remaining. The credit balance is the real budget for bursty AI workloads on burstable VMs, not the published vCPU count.
Before recommending a VM resize or cloud GPU offload for a one-off bursty job, query the current CPU Credits Remaining metric — full credit bank often means the existing burstable VM can handle the job at zero incremental cost.