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- Plan test superseded by live test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"
}Needs a registry token from /account/tokens. The module itself is free; the account is what identifies you. Full setup: registry docs.
Cite it in your README
badge · attributionPaste this beside the module in the repository that uses it. The badge is rendered from this artifact's verification record, so it reads live-tested because the record says so, and the link lands on this page.
[](https://www.iac-bazaar.com/catalog/gcp-vertex-ai?utm_source=syndication&utm_medium=readme&utm_campaign=artifact)
Terraform module 1.0.0, live-tested on IaC Bazaar: [Vertex AI Endpoint](https://www.iac-bazaar.com/catalog/gcp-vertex-ai?utm_source=syndication&utm_medium=readme&utm_campaign=artifact)
```hcl
module "vertex_ai" {
source = "www.iac-bazaar.com/iac-bazaar/gcp-vertex-ai/gcp"
version = "1.0.0"
}
```Preview:
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 module in the catalogue. There is no subscription and nothing to buy - the modules are free to download, and they run under Vizier.
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 need an account
The complete copy-paste usage, the full input/output reference, and operational notes are free with an account - shown here and bundled in the download. Sign in and this section fills in.
- Usage
- Inputs
- Outputs
- Notes
Related modules
gcp-vertex-ai-search
A Vertex AI Search data store in eu, us or global (residency, no default, cannot change), encrypted with a Cloud KMS key of yours (the Google-managed key by name), indexing documents, structured records or a website as you choose, and the search engine over it on the standard tier; the enterprise tier is an input and the LLM add-on, which bills per query, is accepted by name.
huawei-machine-learning
A ModelArts workspace and notebook with allowed_access_ips required, since empty means any address and the notebook has your training data mounted and your credentials in its environment. auth_type PUBLIC means every user in the account rather than the internet. There is no auto-stop argument, and the module says so rather than implying a protection it cannot give.
aws-sagemaker-notebook
AWS defaults a notebook to direct internet access AND root access: a root shell with a path off the network that misses your NAT, routing and DNS firewall, holding a role chosen to read your training data. Both off here, IMDSv2 only.
alicloud-machine-learning
A PAI workspace and the people in it. Created with no members the workspace belongs to whoever ran the apply and the team seeing nothing reads as a permissions problem elsewhere. env_types is fixed at creation and decides whether a dev-to-prod pipeline is even possible, and the role names are the permission model, so each member names their own.
azure-machine-learning
The workspace endpoint is public by default, and the managed network compute runs in defaults to Disabled isolation - unrestricted outbound internet from a network that holds training data. Private workspace, outbound isolation on, high-business-impact flag set so less leaves for Microsoft, identity-based storage access, and a customer-managed key; the four dependencies stay yours.
oci-data-science
A notebook session with no subnet runs on Oracle's network with internet egress and no path to your VCN, and a session left ACTIVE bills its shape - a GPU, over a weekend - whether or not anyone is in it. Sessions attach to your subnet, the shape and storage are set on purpose, and the sessions that are billing from the moment of apply are listed in an output.