Study guide
14.2 Public, Dedicated & Private Endpoints
Google Cloud Professional Machine Learning Engineer PMLE
Track your progress as you read
Finished sections get a check mark.
1 Chapter 1: Exam Overview & the Agent Platform Map
1.1 PMLE Exam Facts, Policies & the June 2026 Blueprint 1.2 From Vertex AI to Gemini Enterprise Agent Platform: The Product Name Map
2 Chapter 2: Low-Code ML with BigQuery ML
2.1 Choosing, Training & Predicting with BigQuery ML Models 2.2 Feature Engineering & Feature Selection in BigQuery ML 2.3 Fine-Tuning & Evaluating Gemini Models from BigQuery
3 Chapter 3: AutoML & Google Cloud AI APIs
3.1 Training Models with Agent Platform AutoML 3.2 Building with Document AI, Vision, Translation & Other AI APIs
4 Chapter 4: Foundation Models in Model Garden
4.1 Evaluating & Selecting Models in Model Garden 4.2 Building & Tuning Solutions with Gemini, Imagen, Veo & MaaS 4.3 Optimizing Gemini Applications for Cost, Latency & Availability
5 Chapter 5: Exploring, Preprocessing & Protecting Data
5.1 Organizing & Exploring Tabular, Text & Image Data 5.2 Choosing a Preprocessing Tool: BigQuery, Dataflow, Spark or Python 5.3 Creating & Consolidating Features in Agent Platform Feature Store 5.4 Protecting PII & Sensitive Data in ML Workflows
6 Chapter 6: Notebooks, Prototyping & Experiment Tracking
6.1 Workbench vs. Colab Enterprise: Secure, Collaborative Notebooks 6.2 Prototyping with PyTorch, scikit-learn, JAX & Model Garden in Notebooks 6.3 Experiment Environments, Tracking & Lineage with Experiments and ML Metadata
7 Chapter 7: Evaluating Predictive & Generative AI Solutions
7.1 Evaluation Metrics for Predictive Models 7.2 Evaluating Gen AI: Computation Metrics, Rubrics & LLM-as-a-Judge
8 Chapter 8: Choosing the Modeling Approach
8.1 Choosing the Model Type: ARIMA, Trees, DNNs & LLMs 8.2 Choosing the Product & Deployment Strategy 8.3 Modeling Techniques for Interpretability Requirements
9 Chapter 9: Training Data & Training SDKs
9.1 Organizing & Ingesting Training Data from Cloud Storage & BigQuery 9.2 Custom Training on Agent Platform: Containers, Jobs & Worker Pools 9.3 Kubeflow on GKE, AutoML & Tabular Workflows as Training Choices
10 Chapter 10: Troubleshooting, Hyperparameter Tuning & Fine-Tuning
10.1 Troubleshooting ML Training Failures 10.2 Hyperparameter Tuning on Agent Platform 10.3 Fine-Tuning Foundation Models & When to Tune
11 Chapter 11: Training Hardware & Distributed Training
11.1 Choosing CPUs, GPUs & TPUs for Training 11.2 Distributed Training: Data & Model Parallelism
12 Chapter 12: Deploying Models for Inference
12.1 Batch vs. Online Inference on Agent Platform 12.2 Serving Beyond Agent Platform Endpoints: Model Garden, Cloud Run & GKE 12.3 Prebuilt & Custom Serving Containers
13 Chapter 13: Model Versions, Rollouts & Inference Logic
13.1 Organizing & Versioning Models in Model Registry 13.2 Rollout Strategies: A/B Tests, Canaries & Traffic Splits 13.3 Inference Preprocessing & Postprocessing
14 Chapter 14: Scaling Online Serving
14.1 Serving Features Online with Feature Store 14.2 Public, Dedicated & Private Endpoints 14.3 Serving Hardware & Autoscaling for Throughput 14.4 Tuning Models for Production Training & Serving
15 Chapter 15: End-to-End ML Pipelines
15.1 Validating Data & Models in Pipelines 15.2 Agent Platform Pipelines with KFP: Components, Templates & Caching 15.3 Ensuring Consistent Preprocessing Between Training & Serving
16 Chapter 16: Orchestration with Managed Airflow & Ray
16.1 Orchestrating ML Workflows with Managed Service for Apache Airflow 16.2 Ray on Agent Platform for Distributed ML Workloads
17 Chapter 17: Automating Retraining & CI/CD/CT
17.1 Choosing a Retraining Policy 17.2 CI/CD/CT for ML with Cloud Build
18 Chapter 18: Securing AI Systems, Responsible AI & Explainability
18.1 Protecting AI Systems from Data & Model Exfiltration 18.2 Defending Gen AI Apps: Safety Filters, Model Armor & Regex Guardrails 18.3 Responsible AI: Detecting & Monitoring Bias 18.4 Model Explainability on Agent Platform
19 Chapter 19: Monitoring AI Solutions
19.1 Configuring Model Monitoring on Agent Platform 19.2 Training-Serving Skew, Data Drift, Concept Drift & Attribution Drift 19.3 Monitoring, Testing & Evaluating Gen AI Solutions in Production
14.2 Public, Dedicated & Private Endpoints
Key Takeaways Explain This Topic AI
Google recommends dedicated public endpoints and dedicated private endpoints using Private Service Connect as best practices for online inference.
Shared public endpoints limit payloads to 1.5 MB, time out at 60 seconds, and have a 30,000 queries-per-minute quota, while dedicated and PSC endpoints allow 10 MB and timeouts up to 1 hour.
Dedicated public endpoints don't support VPC Service Controls, so use a Private Service Connect endpoint inside a perimeter.
Private endpoints based on VPC Network Peering support one model per endpoint, with no traffic splitting and no request-response logging.
Tuned Gemini models can be deployed only to shared public endpoints.
Last updated: September 2026
The exam guide lists deploying models to public and private endpoints . Endpoint choice is mostly a networking and security decision, but it also limits payload size, timeouts, streaming, traffic splitting, and logging.
The Four Endpoint Types
Feature Dedicated public (recommended) Shared public Dedicated private via Private Service Connect (recommended) Private (private services access / VPC peering)
Network access Public internet, dedicated networking plane Public internet, shared plane Private, through a PSC forwarding rule in your VPC Private, through VPC Network Peering
- VPC Service Controls Not supported Supported Supported Supported
- Network latency Optimized Unoptimized Optimized Optimized
- Inference timeout Up to 1 hour 60 seconds Up to 1 hour 60 seconds
- Payload limit 10 MB 1.5 MB 10 MB 10 MB
- QPM quota Unlimited 30,000 Unlimited Unlimited
- Protocols HTTP or gRPC HTTP HTTP or gRPC HTTP
- Streaming (SSE) Yes No Yes No
- Traffic split Yes Yes Yes No (one model per endpoint)
- Request/response and access logging Yes Yes Yes No
- Tuned Gemini deployment No Yes (only option) No No
- AutoML models and explainability No Yes No No
Dedicated and PSC endpoints support predict , rawPredict , streamRawPredict , and Chat Completion (Model Garden). gRPC requests must include the x-vertex-ai-endpoint-id header.
Private Service Connect Endpoints
Private Service Connect (PSC) puts a forwarding rule in your VPC that connects to a service attachment exposing Agent Platform inference. Benefits:
No public IPs, no public internet path, and no peered IP range to plan.
Serve multiple consumer projects and VPCs privately.
Reach from on-premises over Cloud Interconnect or VPN.
Works inside VPC Service Controls perimeters.
Keeps dedicated-endpoint features such as streaming, gRPC, traffic splitting, and logging.
Google recommends PSC when inference must be private, secure, low latency, and not publicly accessible .
Private Services Access Endpoints (VPC Peering)
The older private option peers your VPC with the Agent Platform service network. Limitations to know:
One model per endpoint , so no traffic splitting for canaries or A/B tests.
No request-response or access logging.
60-second timeout and no streaming.
Supports AutoML tabular and custom-trained models.
Needs a reserved IP range and an active peering connection.
If a scenario needs private access and canary rollouts or logging for monitoring, choose PSC , not VPC peering.
Choosing an Endpoint
- Scenario Endpoint
- Public mobile app backend, large image payloads, gen AI streaming Dedicated public
- Quick prototype, small payloads, or deploying a tuned Gemini model Shared public
Bank serving models to internal apps in several VPCs and on-premises, with a VPC Service Controls perimeter, canary rollouts, and logging Private Service Connect
- Existing peered architecture with a single model and no traffic splitting needs Private (VPC peering)
- Regulated workload that forbids public internet paths but still needs streaming Private Service Connect
- Security Layers Beyond the Endpoint Type
IAM: callers need permission to invoke the endpoint (for example, through the Agent Platform User role or a custom role scoped to prediction). Use service accounts for applications.
VPC Service Controls: keep endpoints, models, and training data inside a perimeter to reduce exfiltration risk (Chapter 18).
CMEK: encrypt model artifacts and endpoint resources with customer-managed keys where policy requires.
Deployed model service account: give the serving container a least-privilege identity for any Google Cloud calls it makes.
Audit logs: Cloud Audit Logs record administrative actions such as deploy and undeploy.
How Clients Reach a Private Service Connect Endpoint
Create the endpoint with Private Service Connect enabled, and list the consumer projects allowed to connect.
In each consumer VPC, create a forwarding rule (the PSC endpoint) with an internal IP address that targets the endpoint's service attachment .
Optionally create a private DNS record so applications call a stable hostname instead of an IP address.
Applications in that VPC, and on-premises systems connected through Cloud Interconnect or VPN, send requests to that internal address with normal IAM authentication.
Deploy models and manage traffic splits on the endpoint as usual. The network path stays private.
Migrating Between Endpoint Types
An endpoint's networking type is set when the endpoint is created, so the usual pattern is to create the new endpoint (for example, PSC), deploy the same model version to it, move clients over gradually (DNS or configuration change), and then undeploy from the old endpoint. Keep the Model Registry version identical so predictions don't change during the move.
Common Mistakes
Choosing a dedicated public endpoint for a workload that must sit inside a VPC Service Controls perimeter.
Choosing a VPC-peering private endpoint and later discovering that canary rollouts and request logging aren't possible.
Sending large base64 payloads to a shared public endpoint and hitting the 1.5 MB limit.
Exposing internal-only models publicly and relying on IAM alone when policy forbids public paths.
Performance Notes
Dedicated and private endpoints have optimized network latency compared with shared public endpoints.
Large payloads such as images are better sent as Cloud Storage URIs when possible, even when 10 MB is allowed.
Use gRPC on dedicated or PSC endpoints for lower serialization overhead at high QPS.
Keep clients and endpoints in the same region .
Worked Scenario
A hospital network serves an imaging model to clinical apps. Requirements: no public exposure, a VPC Service Controls perimeter around PHI, 4 MB DICOM-derived payloads, gradual rollout of new versions, and request logging for audits.
Shared public fails the payload limit and public exposure rules. Dedicated public fails VPC Service Controls. VPC-peering private endpoints fail traffic splitting and logging.
Answer: a dedicated private endpoint using Private Service Connect.