# GCP Vertex AI optimization | Cloud Efficiency Hub

Canonical: https://www.pointfive.co/efficiency-hub/cloud-services/gcp-vertex-ai

5 documented GCP Vertex AI cost inefficiencies, each with how to detect it and how to fix it.

[Cloud Efficiency Hub](https://www.pointfive.co/efficiency-hub) 

5 documented GCP Vertex AI cost inefficiencies, each with how to detect it and how to fix it.

## 5 inefficiencies

[All services](https://www.pointfive.co/efficiency-hub#browse-by-service)

- GCP Vertex AI  CER-0267

### [Using High-Cost Models for Low-Complexity Tasks in Vertex AI](https://www.pointfive.co/efficiency-hub/inefficiencies/using-high-cost-models-for-low-complexity-tasks-bec92)

Vertex AI workloads often include low-complexity tasks such as classification, routing, keyword extraction, metadata parsing, document triage, or summarization of short and simple text. These operations do not require the advanced...

AI

- GCP Vertex AI  CER-0512

### [Underutilized Vertex AI Provisioned Throughput](https://www.pointfive.co/efficiency-hub/inefficiencies/underutilized-vertex-ai-provisioned-throughput)

Provisioned Throughput on Vertex AI, now documented under the Gemini Enterprise Agent Platform name, is a fixed-cost, fixed-term subscription that reserves throughput for a specific generative AI model in a specific region. It is bought in...

AI

- GCP Vertex AI  CER-0556

### [Vertex AI Workbench Instances With Idle Shutdown Disabled](https://www.pointfive.co/efficiency-hub/inefficiencies/vertex-ai-workbench-instances-with-idle-shutdown-disabled)

Vertex AI Workbench instances, now documented as Agent Platform Workbench under the Gemini Enterprise Agent Platform name, are notebook VMs that bill for CPU, memory and any attached GPUs whenever they are running. To help manage costs,...

AI

- GCP Vertex AI  CER-0567

### [Idle Vertex AI Endpoints With Deployed Models](https://www.pointfive.co/efficiency-hub/inefficiencies/idle-vertex-ai-endpoints-with-deployed-models)

When a model is deployed to a Vertex AI endpoint for online inference on dedicated resources (the service is now documented as Agent Platform Inference under the Gemini Enterprise Agent Platform name), each replica is a VM that bills...

AI

- GCP Vertex AI  CER-0568

### [Latency-Tolerant Gemini Workloads on Vertex AI Not Using Batch or Flex](https://www.pointfive.co/efficiency-hub/inefficiencies/latency-tolerant-gemini-workloads-on-vertex-ai-not-using-batch-or-flex)

Many Gemini workloads on Vertex AI, now documented under the Gemini Enterprise Agent Platform name, do not need an answer in seconds: bulk classification and tagging, extraction from document archives, translation, catalog enrichment,...

AI

## More GCP services

- [GCP Compute Engine  14](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-compute-engine)

- [GCP BigQuery  9](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-bigquery)

- [GCP GKE  9](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-gke)

- [GCP Cloud SQL  8](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-cloud-sql)

- [GCP GCS  6](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-gcs)

- [GCP Cloud Logging  5](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-cloud-logging)

- [GCP Dataflow  4](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-dataflow)

- [GCP Cloud Run  3](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-cloud-run)

- [GCP Cloud Memorystore  2](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-cloud-memorystore)

- [GCP Cloud NAT  2](https://www.pointfive.co/efficiency-hub/cloud-services/gcp-cloud-nat)

---
Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.