Google Vertex AI

Route Pullfrog's model calls through Vertex AI in your own Google Cloud project. Use it when your team already buys through Google Cloud, holds Vertex model-access approvals, or wants Google Cloud's audit and billing controls around inference.

Setup

Store a service-account key

Create a Google Cloud service account with the roles/aiplatform.user role and download a JSON key. In the Pullfrog console, click Set up on the Google Vertex AI tile of the Providers card and paste the whole JSON object as VERTEX_SERVICE_ACCOUNT_JSON.

You can store it as a GitHub Actions secret instead and map it in the workflow's env: block.

Set the project, location and model in your workflow

Add these to the workflow's env: block. None of them is secret.

.github/workflows/pullfrog.yml
- name: Run agent
  uses: pullfrog/pullfrog@v0
  with:
    prompt: ${{ inputs.prompt }}
  env:
    GOOGLE_CLOUD_PROJECT: my-project
    VERTEX_LOCATION: global
    VERTEX_MODEL_ID: <vertex-model-id>
    # only when the key is a GitHub Actions secret
    VERTEX_SERVICE_ACCOUNT_JSON: ${{ secrets.VERTEX_SERVICE_ACCOUNT_JSON }}

Enable the API and the model

Enable the Vertex AI API (aiplatform.googleapis.com) for the project, then enable any gated model in Model Garden.

Pick the model

Open the Model card's editor, choose Manual and pick Google Vertex AI from the model menu.

Variables

NameSecretPurpose
VERTEX_SERVICE_ACCOUNT_JSONYesThe full service-account JSON key, not a file path.
GOOGLE_CLOUD_PROJECTNoProject ID. Optional when the JSON key has a project_id.
VERTEX_LOCATIONNoVertex location. Use global unless data residency needs a regional endpoint.
VERTEX_MODEL_IDNoExact Vertex model ID. Pullfrog runs it as written and never upgrades it.

A value stored in the console needs no env: line, because Pullfrog injects it into every run. A value set in the workflow wins over a stored one.

Model IDs

The model menu has a single Google Vertex AI entry; VERTEX_MODEL_ID names the actual model. Use the ID that Model Garden shows for a Claude, Gemini or partner model your project has enabled, and edit the variable to change models.

Routing

Pullfrog reads the model ID to choose the agent:

  • Claude models, whose ID starts with claude-, run on Claude Code. Pullfrog sets CLAUDE_CODE_USE_VERTEX=1 and passes the project and location in Claude Code's own variable names.
  • Every other model runs on OpenCode's google-vertex provider.

Troubleshooting

SymptomFix
"VERTEX_MODEL_ID must be set when the model is vertex/byok"The repository uses Google Vertex AI, but the workflow does not set VERTEX_MODEL_ID. Add it to env:.
"Google Vertex AI is missing required settings"The message lists each missing value: VERTEX_SERVICE_ACCOUNT_JSON, GOOGLE_CLOUD_PROJECT (when the key has no project_id), VERTEX_LOCATION, or VERTEX_MODEL_ID.
Google authentication errorVERTEX_SERVICE_ACCOUNT_JSON must hold the JSON object itself, not a file path. Pullfrog writes it to a credentials file on the runner and sets GOOGLE_APPLICATION_CREDENTIALS for the agent.
Permission or model-access errorCheck that the service account has roles/aiplatform.user, the Vertex AI API is on, and the model is enabled in Model Garden for VERTEX_LOCATION.
© 2026 Pullfrog, Inc.

On this page