Vertex AI Endpoint
A Vertex AI Endpoint for online prediction with optional CMEK, optional Private Service Access networking and request/response logging - model deployment left to you, so it stands up for cents.
Verification
Live-testedReally deployed to a cloud sandbox, verified against its outputs and assertions, then destroyed - with the teardown confirmed.
Conformance
- Static validation (fmt · validate · tflint)
- Security scan clean (Checkov)
- Plan test superseded by live test
Provenance
- SHA-256 checksum
- Cosign signature
Functional
- Live-tested - applied, verified, destroyed
Last verified 2026-06-30 · how we verify
Verify this download
cosign · sha-256Don't take our word for it. Every release is signed with cosign - check the bytes against our pinned public key before you trust them.
# 1. Our pinned public key - fetch once, trust out-of-band
curl -O https://www.iac-bazaar.com/cosign.pub
# 2. This module's Sigstore bundle
curl -o gcp-vertex-ai-1.0.0.sigstore.json \
https://www.iac-bazaar.com/api/artifacts/gcp-vertex-ai/signature
# 3. Verify the tarball you downloaded
cosign verify-blob \
--key cosign.pub \
--bundle gcp-vertex-ai-1.0.0.sigstore.json \
gcp-vertex-ai-1.0.0.tar.gz
# → Verified OK
# 4. (optional) confirm the checksum too
echo "067caf7310dd5eacf1f53ea0f1dbef7eafac75797df513bde875a6c574787f54 gcp-vertex-ai-1.0.0.tar.gz" | sha256sum -cUse it from the registry
terraform · opentofumodule "vertex_ai" {
source = "www.iac-bazaar.com/iac-bazaar/gcp-vertex-ai/gcp"
version = "1.0.0"
}Paid module — needs a purchase (or a subscription that covers it) plus a registry token from /account/tokens. Full setup: registry docs.
Inputs & outputs
Create a free account to read this module's contract
The declared contract — every input name, type, default and description, plus every output — is shown to signed-in accounts, not to anonymous visitors.
A free account sees the contract of every Free module. This one is Basic, so its contract unlocks when you buy it.
Documentation
gcp-vertex-ai
A Vertex AI Endpoint — the regional serving surface you deploy trained models
behind for online prediction. The endpoint is a free control-plane object; cost
only begins when you deploy a model (the replica VMs). This module provisions the
endpoint with optional CMEK, optional private (Private Service Access) networking
and optional request/response logging, and leaves model deployment to you — so it
stands up and tears down for cents. Works with Terraform and OpenTofu
(>= 1.6), Google provider >= 7.0, < 8.0.
Defaults:
- Public endpoint (
network = null) reachable over the Google API surface - Google-managed encryption (
kms_key_name = null) - No request/response logging unless you opt in
This module deliberately creates no VMs, notebooks or Workbench instances (those are billed compute). To actually serve predictions, deploy a model to the endpoint separately (
google_vertex_ai_endpoint_with_model_garden_deploymentorgcloud ai endpoints deploy-model).
Requirements
- Terraform or OpenTofu
>= 1.6 hashicorp/google>= 7.0, < 8.0- API:
aiplatform.googleapis.com
License
Commercial — IaC Bazaar EULA. © IaC Bazaar. Original work (not derived from a third-party module).
Usage code & full reference unlock after purchase
The complete copy-paste usage, the full input/output reference, and operational notes ship with your licence - shown here and bundled in the download.
- Usage
- Inputs
- Outputs
- Notes