Google Cloud Vertex AI (Agent Platform)

Vertex's OpenAI-compatible endpoint, with a short-lived OAuth access token as the bearer (Application Default Credentials — mint it with gcloud auth print-access-token, or from a service account in your deploy; rotate it before the hour is up). Model ids are prefixed with the publisher (google/, meta/, anthropic/… for Model Garden).

bash

LLM_CHAIN=vertex,anthropic   # failover to a second endpoint is one more name
LLM_VERTEX_BASE=https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT/locations/us-central1/endpoints/openapi
LLM_VERTEX_API_KEY=$(gcloud auth print-access-token)
LLM_VERTEX_MODEL=google/gemini-2.5-pro

Every endpoint takes the same knobs: LLM_<NAME>_TEMPERATURE (none omits it), LLM_<NAME>_BODY (JSON merged into every request), LLM_<NAME>_PRICE (input,cached,output per million, for the cost ledger), LLM_<NAME>_NOTES (a per-model notes file). Two models of one provider: LLM_FAST_PRESET=vertex under another name. Environment has the full list.

Check it: npm run gateway, then curl localhost:8787/api/health — the llm.chain entry shows the endpoint, whether its key is set, and its state.

Provider docs: https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai

Source: docs/providers/vertex.md — edit it there; the site mirrors the repository.

Google Cloud Vertex AI (Agent Platform) ​

Google Cloud Vertex AI (Agent Platform)