Bedrock Provisioned Throughput on Older Model Generation
Provisioned throughput is committed and billed per model unit for the term, so committing it to a superseded model locks spend to a generation the newer one outperforms.
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: Migrate the Provisioned Throughput to a newer model. 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
- Identify the latest generation in the same model family. E.g. Anthropic Claude 3.5/4 family, Amazon Titan v2, Meta Llama 3.x, Cohere Command R/R+.
- Benchmark output quality on a representative prompt set (use Bedrock's model evaluation if you can spare a few hours of bench cost).
- Bedrock → Provisioned Throughput → Create → target the newer model-id with the same MU count.
- Update calling code's modelId / provisionedModelArn.
- Shift traffic gradually; watch quality + latency.
- Bedrock → Provisioned Throughput → the resource (old PT) → Delete once traffic is fully migrated.
These are the steps the finding carries in the product.
- 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-1610- 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.