Skip to main content

Vertex AI

The gateway speaks Vertex AI natively — Gemini, Claude-on-Vertex, Llama.

What's specific to Vertex AI

PropertyValue
Provider idvertex-ai
Gateway speaksVertex REST ({region}-aiplatform.googleapis.com)
CredentialService-account JSON + project id + region, server-held
SigningOAuth2 access token minted from the service account
Client base URLOPENAI_BASE_URL (Gemini/Llama) or ANTHROPIC_BASE_URL (Claude) → :8787

Everything shared — self-hosting, the config-based redirect, how credentials are stored — is documented once in the gateway.

Configure the provider

Console → Providers → add vertex-ai:

  • Project ID — your GCP project id (or read from the JSON's project_id)
  • Region — the region serving the model, e.g. us-east5 (availability is region-specific)
  • Service account JSON — paste a key with the Vertex AI User role

The host doesn't need to be a GCE VM — the service account is the credential, so any Docker host in your project works (in-project is still the right place for data-boundary reasons).

Running it in GKE

The same stack runs unchanged in a GKE cluster — point workloads' base-URL env at the gateway's in-cluster Service. See Get started → Install.

Route requests to it

# Gemini / Llama via OpenAI SDKs:
export OPENAI_BASE_URL=http://<gateway>:8787/v1
# Claude-on-Vertex via Anthropic SDKs (Claude Code):
export ANTHROPIC_BASE_URL=http://<gateway>:8787
# requests carry: x-anyray-provider: vertex-ai

Models use Vertex ids, e.g. gemini-1.5-pro-002, claude-3-5-sonnet-v2, llama-3.1-405b-instruct-maas.