749432fefc
- .aurelio/garden/: model + agent garden (Google Cloud entries) - .aurelio/mirrors/: sync-mirrors.yaml + state tracking - .aurelio/skills/gcp/: Google Cloud skill - Consolidation audit + execution plan (2026-07-30) - vault-sync.py: Obsidian → GBrain MCP ingestion daemon - brain-to-gbrain.py: brain → GBrain migration tool - Provider registry + dist mirrors updated - .gitignore: exclude .runner, .mimocode/.cron-lock, drift/target Co-authored-by: Álvaro de Campos <campos@portugalfuturista.org>
122 lines
3.2 KiB
YAML
122 lines
3.2 KiB
YAML
# PF Model Garden — Google Cloud (Vertex AI)
|
|
#
|
|
# Enterprise Google Cloud models exposed through the Aurelio ecosystem.
|
|
# These are distinct from the consumer Gemini (AI Studio) provider.
|
|
|
|
provider: google-cloud
|
|
label: Google Cloud Vertex AI
|
|
protocol: gemini
|
|
auth:
|
|
kind: service_account
|
|
env: GOOGLE_APPLICATION_CREDENTIALS
|
|
fallback_env: GOOGLE_CLOUD_API_KEY
|
|
region_default: europe-west1
|
|
|
|
models:
|
|
- id: gemini-2.5-pro-preview-06-05
|
|
name: Gemini 2.5 Pro
|
|
kind: chat
|
|
publisher: google
|
|
context_window: 1000000
|
|
surfaces:
|
|
- dirac
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
input_per_1m_tokens: 1.25
|
|
output_per_1m_tokens: 10.00
|
|
currency: USD
|
|
notes: Approximate; region and batch mode affect rate. Check cloud.google.com/vertex-ai/generative-ai/pricing.
|
|
|
|
- id: gemini-2.5-flash-preview-06-05
|
|
name: Gemini 2.5 Flash
|
|
kind: chat
|
|
publisher: google
|
|
context_window: 1000000
|
|
surfaces:
|
|
- dirac
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
input_per_1m_tokens: 0.15
|
|
output_per_1m_tokens: 0.60
|
|
currency: USD
|
|
notes: Fast, low-cost; good for agentic loops and classification.
|
|
|
|
- id: gemini-2.0-flash-001
|
|
name: Gemini 2.0 Flash
|
|
kind: chat
|
|
publisher: google
|
|
context_window: 1000000
|
|
surfaces:
|
|
- dirac
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
input_per_1m_tokens: 0.10
|
|
output_per_1m_tokens: 0.40
|
|
currency: USD
|
|
notes: Stable GA model.
|
|
|
|
- id: imagen-3-0-generate-001
|
|
name: Imagen 3
|
|
kind: image
|
|
publisher: google
|
|
context_window: null
|
|
surfaces:
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
per_image: 0.04
|
|
currency: USD
|
|
notes: Per image at 1024x1024; higher resolutions cost more.
|
|
|
|
- id: veo-2-0-generate-001
|
|
name: Veo 2
|
|
kind: video
|
|
publisher: google
|
|
context_window: null
|
|
surfaces:
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
per_second: 0.05
|
|
currency: USD
|
|
notes: Per generated video second; minimum length applies.
|
|
|
|
- id: text-embedding-004
|
|
name: Text Embedding 004
|
|
kind: embedding
|
|
publisher: google
|
|
context_window: null
|
|
dimensions: 2048
|
|
surfaces:
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
per_1m_tokens: 0.10
|
|
currency: USD
|
|
notes: Input-only embedding model.
|
|
|
|
- id: multimodalembedding@001
|
|
name: Multimodal Embedding
|
|
kind: embedding
|
|
publisher: google
|
|
context_window: null
|
|
dimensions: [128, 256, 512, 1408]
|
|
surfaces:
|
|
- mcp
|
|
- portal
|
|
pricing_proxy:
|
|
per_1m_tokens: 0.20
|
|
currency: USD
|
|
notes: Mixed image+text embeddings; dimensions selectable.
|
|
|
|
endpoints:
|
|
chat_template: "https://{region}-aiplatform.googleapis.com/v1/projects/{project}/locations/{region}/publishers/google/models/{model_id}:generateContent"
|
|
stream_template: "https://{region}-aiplatform.googleapis.com/v1/projects/{project}/locations/{region}/publishers/google/models/{model_id}:streamGenerateContent"
|
|
|
|
notes:
|
|
- Model availability and pricing vary by region; verify before production use.
|
|
- Use service-account auth in production; API-key fallback is for quick tests only.
|
|
- The separate `gemini` provider in .aurelio/providers/registry.yaml targets AI Studio (consumer), not Vertex AI.
|