Bedrock Provisioned Throughput Below Break-Even
Provisioned throughput is billed for the model units it reserves for the whole commitment term, so below a certain request volume on-demand invocation costs less for the same traffic.
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: Move the Provisioned Throughput to on-demand pricing. 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 → InvocationCount / InputTokenCount on the resource for 30 days. Confirm traffic is sporadic, not steady.
- Estimate on-demand cost: total input tokens × per-1k input price + output tokens × per-1k output price (Bedrock pricing page).
- Compare against the monthly PT fee. If on-demand wins by ≥20%, migrate.
- Update calling code to invoke the foundation model directly (InvokeModel against the base model-id, no PT ARN).
- Deploy and shift traffic gradually (canary 10% → 50% → 100%).
- Bedrock → Provisioned Throughput → the resource → Delete once cutover is complete.
These are the steps the finding carries in the product.
- Category
- Commitment discounts. Reserved Instance, Savings Plan and Committed Use opportunities, where steady usage justifies a commitment.
- Where it appears
- The Savings tab of Recommendations, with every affected resource listed.
- Rule ID
RC-1603- Full reference
Related checks
See the discount opportunities 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.