GCP Vertex AI Model Not Deployed
An undeployed model is stored and billed but serves no prediction traffic, nothing can call it until it is deployed to an endpoint.
Free to start. No card. The playground just needs your work email.
Google Cloud
Found, explained, handed over.
Findings with a dollar figure attached, idle, oversized, orphaned, unscheduled and undiscounted spend.
Detect
ZopNight checks this automatically across Google Cloud, with read-only access to the account.
Explain
Every finding says exactly what to change: Delete the undeployed Vertex AI 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
- Vertex AI Models on Google Cloud
- The fix, by hand
- Confirm the model version is not pending deployment.
- Export/archive the artifact if it has value.
- Delete the unused model from the Vertex AI Model Registry.
These are the steps the finding carries in the product.
- Category
- Orphaned resources. Resources no longer attached to anything that needs them, such as unattached volumes and unassigned IPs.
- Where it appears
- The Savings tab of Recommendations, with every affected resource listed.
- Rule ID
RC-1214- Full reference
Related checks
See the orphaned 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.