II.
Provider overview
Reference · liveprovider:gcp-vertex
Google Cloud Vertex AI overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for provider:gcp-vertex.
Attributes
displayName
Google Cloud Vertex AI
vendor
Google Cloud
versionRange
>=v1
authMethods
- service-account
- oauth
- workload-identity
- gcp-adc
authMethodNotes
Vertex requires GCP IAM. Local dev uses Application Default
Credentials (`gcloud auth application-default login`); production
workloads use Workload Identity (GKE / Cloud Run) or service-account
JSON. Caller MUST have `aiplatform.endpoints.predict` (and
`aiplatform.endpoints.streamRawPredict` for streaming). The publisher
model (e.g. `publishers/anthropic/models/claude-opus-4-7`) MUST be
enabled for the GCP project.
endpoints
base
publishers_anthropic_messages
publishers_google_generate_content
pricing
See https://cloud.google.com/vertex-ai/generative-ai/pricing for
Vertex-published model pricing. Vertex passes through model
pricing for Anthropic and Google models with a multi-region surcharge.
pricingTiers
- nameon-demandrateLimitPer-project online prediction quotas (RPM) per region per publisher modelpriceMultiplier1descriptionDefault per-token billing via :rawPredict / :generateContent.
- nameprovisioned-throughputrateLimitReserved GSU (Generative AI Scale Units) per region per modelpriceMultiplier1descriptionVertex Provisioned Throughput — committed capacity in GSU.
- namebatchrateLimitAsync batch prediction jobs; backed by Cloud Storage / BigQuerypriceMultiplier0.5descriptionVertex Batch Prediction — discounted async.
rateLimitSignalingProtocol
Quota errors return HTTP 429 with gRPC `code: 8 (RESOURCE_EXHAUSTED)`
in the standard Google error envelope `{ "error": { "code": 429,
"status": "RESOURCE_EXHAUSTED", "message": ..., "details": [...] } }`.
`x-goog-request-id` always present. Use Cloud Quotas API to inspect
current limits.
dataResidencyOptions
vendorFeatures
slaTier
gcp-vertex-99.9
regions
- us-central1
- us-east1
- us-east4
- us-east5
- us-west1
- us-west4
- europe-west1
- europe-west2
- europe-west4
- europe-west9
- asia-southeast1
- asia-northeast1
Outgoing edges
realizes1
- layer:2-provider·LayerProvider
serves12
- model:claude-opus-4-7@current·ModelVersionClaude 4.7 Opus
- model:claude-opus-4-6@current·ModelVersionClaude 4.6 Opus
- model:claude-opus-4-5@current·ModelVersionClaude 4.5 Opus
- model:claude-opus-3@current·ModelVersionClaude 3 Opus
- model:claude-sonnet-4-6@current·ModelVersionClaude 4.6 Sonnet
- model:claude-sonnet-4-5@current·ModelVersionClaude 4.5 Sonnet
- model:claude-sonnet-3-5@current·ModelVersionClaude 3.5 Sonnet
- model:claude-haiku-4-5@current·ModelVersionClaude 4.5 Haiku
- model:gemini-3-1-pro@current·ModelVersionGemini 3.1 Pro
- model:gemini-2-5-pro@current·ModelVersionGemini 2.5 Pro
- model:gemini-2-5-flash@current·ModelVersionGemini 2.5 Flash
- model:gemini-2-0-flash@current·ModelVersionGemini 2.0 Flash
supports2
- capability:supports-vertex-reasoning-engine·CapabilitySupports Vertex Reasoning Engine
- capability:model-discovery·CapabilityModel discovery
Incoming edges
bridges_for3
- adapter:transport-adapter·Adaptertransport-adapter
- adapter:transport-adapter·Adaptertransport-adapter
- adapter:transport-adapter·Adaptertransport-adapter
served_by24
- model-transport:vertex-anthropic-messages·ModelTransportProtocolVertex AI — Anthropic Messages
- model:claude-fable-5@current·ModelVersionClaude Fable 5
- model:claude-haiku-4-5@current·ModelVersionClaude 4.5 Haiku
- model:claude-mythos-5@current·ModelVersionClaude Mythos 5
- model:claude-opus-3@current·ModelVersionClaude 3 Opus
- model:claude-opus-4-5@current·ModelVersionClaude 4.5 Opus
- model:claude-opus-4-6@current·ModelVersionClaude 4.6 Opus
- model:claude-opus-4-7@current·ModelVersionClaude 4.7 Opus
- model:claude-sonnet-3-5@current·ModelVersionClaude 3.5 Sonnet
- model:claude-sonnet-4-5@current·ModelVersionClaude 4.5 Sonnet
- model:claude-sonnet-4-6@current·ModelVersionClaude 4.6 Sonnet
- model:gemini-2-0-flash@current·ModelVersionGemini 2.0 Flash
- model:gemini-2-5-flash-image@current·ModelVersionGemini 2.5 Flash Image
- model:gemini-2-5-flash@current·ModelVersionGemini 2.5 Flash
- model:gemini-2-5-pro@current·ModelVersionGemini 2.5 Pro
- model:gemini-3-1-deep-think@current·ModelVersionGemini 3.1 Deep Think
- model:gemini-3-1-flash-image@current·ModelVersionGemini 3.1 Flash Image
- model:gemini-3-1-flash-lite@current·ModelVersionGemini 3.1 Flash Lite
- model:gemini-3-1-pro@current·ModelVersionGemini 3.1 Pro
- model:gemini-3-5-flash@current·ModelVersionGemini 3.5 Flash
- model:gemini-3-flash@current·ModelVersionGemini 3 Flash
- model:gemini-3-pro-image@current·ModelVersionGemini 3.1 Pro Image
- model:gemini-3-pro@current·ModelVersionGemini 3 Pro
- model:claude-opus-4-8@current·ModelVersionClaude Opus 4.8