Bedrock Provisioned Throughput Underutilised
Model units are billed for the whole commitment term whether or not requests consume them.
Free to start. No card. The playground just needs your work email.
AWS
Found, explained, handed over.
Findings with a dollar figure attached, idle, oversized, orphaned, unscheduled and undiscounted spend.
Detect
ZopNight checks this automatically across AWS, with read-only access to the account.
Explain
Every finding says exactly what to change: Reduce model units on the Provisioned Throughput. Where the saving can be proven it is priced; where it cannot, the finding says so.
Fix
The finding opens with the fix already written out, step by step, so it is one ticket, not an investigation.
- Applies to
- Bedrock Provisioned Throughput on AWS
- The fix, by hand
- CloudWatch → Bedrock → InputTokenCount + OutputTokenCount over the last 30 days (
bedrockPTUnderutilizedLookbackDays). - Compute the smallest Model Unit count that comfortably covers peak throughput.
- Bedrock → Provisioned Throughput → Modify → reduce ModelUnits (or recreate at a lower MU count).
- Watch p95 invocation latency for 24h. Raise MU back up if it crosses SLA.
These are the steps the finding carries in the product.
- CloudWatch → Bedrock → InputTokenCount + OutputTokenCount over the last 30 days (
- Category
- Rightsizing. Resources sized for headroom they never use. A smaller size runs the same workload for less.
- Where it appears
- The Savings tab of Recommendations, with every affected resource listed.
- Rule ID
RC-1602- Full reference
Related checks
See the oversized resources in your account.
Connect a read-only role and the first pass runs on your own estate. This check, and the rest of the catalogue, with it.
Prefer to talk it through first? Book 20 minutes with the team.
- $30M+annualised cloud spend under management
- 550K+resources tracked since launch
- 20-60%off the bill in the first month
- SOC 2Type II report, plus ISO 27001
Figures published on zop.dev.