local-first · v0.1

Google Vertex AI

Managed model hosting on Google Cloud.

llmactiveenterprise-ready#6f9003d6

Supported adapters (this provider can fulfill)

One adapter supports many providers. The default is switchable without changing any workflow.

Served capabilities (derived via adapters)

embeddingllmreasoningspeechvision

Authentication & secrets

authenticationservice_account
auth noteGCP service account
required secretsGOOGLE_APPLICATION_CREDENTIALS
permissions

Secrets are referenced by name only — never values. This runtime performs no OAuth and stores no credentials.

Approval & compliance

requires approvalfalse
approval kinds
complianceSOC2
enterprise readytrue

Pricing

modelper_token
unitUSD / 1K tokens
note

Latency & limits

latencymedium
max concurrency
rate limit / min
quotaunbounded (request)

Availability & regions

globaltrue
regionsglobal
healthunknown

Deployment targets (without redesign)

gcphybridenterprise
execution modesapi, cloud

Dependencies & future dispatch

depends on

Providers describe themselves only. Selection and execution are owned by the future Dispatch Runtime — this layer dispatches nothing.