selan.ai

Docs · Google Vertex

Connect Google Vertex

Run Claude on a Google Cloud project you own, so the inference lands on your Google invoice instead of ours. Five steps, two of them commands. For how connecting a provider fits together, start at the docs.

What you are setting up

Selan holds no key to your Google account. Instead you grant one Google service account (ours) a single role on a project you own, and we mint a short-lived token at the moment of each request. We store nothing long-lived, and you can revoke the grant in one command without involving us.

The account you grant is: 

selan-vertex@selan-prod.iam.gserviceaccount.com

It has no privileges of its own anywhere. Everything it can do on your project comes from you, and it is deliberately not the identity Selan's own application runs as.

Use a project of its own. With a new, empty project, the role you grant reaches nothing else you run, and the Claude spend stays cleanly attributable on your bill. It also makes for a much shorter conversation with whoever approves access. Connecting your main production project works, and asks far more of you than it needs to.

The five steps

Replace YOUR_PROJECT throughout with the project id you are connecting. Steps 1 and 2 happen in the Google Cloud console; 3 and 4 are the commands the Selan dialog shows you with your project already filled in.

1. Create a project and link billing.

gcloud projects create YOUR_PROJECT --name="Selan Vertex"

Then link a billing account to it in Billing. Vertex will refuse to serve a project with no billing attached, and the error does not say so in as many words.

2. Enable Claude in Model Garden.

Open Model Garden, search for Claude, open the model you want and press Enable. This is where you accept Anthropic's terms, and it is per project. A project that has not been through it has no Claude quota at all, which is the single most common reason a connection fails.

3. Switch the Vertex API on.

gcloud services enable aiplatform.googleapis.com --project YOUR_PROJECT

4. Grant Selan the one role it needs.

gcloud projects add-iam-policy-binding YOUR_PROJECT --member=serviceAccount:selan-vertex@selan-prod.iam.gserviceaccount.com --role=roles/aiplatform.user

5. Request Claude quota.

A new project starts at zero quota, and no command grants it. Open Quotas, filter on anthropic, and request an increase on global_online_prediction_requests_per_base_model for each Claude model you intend to use. Quota is granted per model, so one grant does not cover the others. Google reviews the request, so it is not instant.

Connecting it in Selan

In Selan, open Tokens → Add token and choose Google Vertex as the provider. Enter the project id, choose a location, and press Add.

Add is not a save button. It first runs one real token of inference against your project, and if anything is missing it names the step to go back to instead of showing a status code. We store nothing unless that call succeeds.

LocationWhat it means
Global Google routes to wherever there is capacity. It has the best availability and no price premium, and it is the only tier that carries every current Claude model. Choose this unless you have a reason not to.
United States Requests stay within US regions. Google charges a 10% premium over global.
European Union Requests stay within EU regions. Google charges a 10% premium over global.

We deliberately do not offer specific regions such as europe-west1. Google serves Claude from them, but only up to older models. Picking one would build a connection that fails on exactly the models you are most likely to ask for.

When it refuses

Each refusal names the step that is missing. These are the four you are likely to see.

What Selan saysWhat to do
…has no Claude quota yet Step 5, and usually step 2 before it. This is the ordinary first attempt, and the wait is Google's, not ours.
The Vertex AI API is not switched on for… Step 3. The command is idempotent, so running it again is safe.
…has not granted Selan access Step 4. Check the project id in the command matches the one you typed.
Google has no Claude in location for… Google does not serve the model on that tier. Switch the location to Global.

Turning it off

Remove the connection in Selan, or revoke the grant on your side. Either one stops it. Revoking on your side is absolute, and does not depend on us doing anything: 

gcloud projects remove-iam-policy-binding YOUR_PROJECT --member=serviceAccount:selan-vertex@selan-prod.iam.gserviceaccount.com --role=roles/aiplatform.user

Selan stores no key for your Google account, so there is nothing left behind to rotate or expire. The next request fails to authenticate, and the connection stops being used.