Generative AI on Vertex AI Google and Partner models and features
are available for specific regions and multi-regions.
A multi-region is a large geographic area, such as the
United States, that contains two or more regions. Multi-region locations can
provide larger quotas than single regions.
Data at rest
Google stores your data at rest only within the selected region or
multi-region for Generative AI on Vertex AI models and features.
Generative AI on Google Cloud models and partner model availability
Google and partner models for Generative AI on Vertex AI are
available in the following regions:
United States
|
Multi-region |
Columbus, Ohio (us-east5) |
Dallas, Texas (us-south1) |
Iowa (us-central1) |
Las Vegas, Nevada (us-west4) |
Moncks Corner, South Carolina (us-east1) |
Northern Virginia (us-east4) |
Oregon (us-west1) |
Gemini 1.5 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.5 Flash |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
PaLM 2 for Text Unicorn |
✔ |
PaLM 2 for Text |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
PaLM 2 for Chat |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
Codey for Code Chat, Codey for Code Completion |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
Embeddings for Text |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Embeddings for Multimodal |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen for Captioning & VQA |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
Imagen (imagegeneration@002 ) |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 2 (imagegeneration@006 ) |
✔ |
|
|
✔ |
✔ |
|
✔ |
✔ |
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Chirp |
✔ |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
✔ |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Agents |
✔ |
Canada
|
Montréal (northamerica-northeast1) |
Gemini 1.5 Pro |
✔ |
Gemini 1.5 Flash |
✔ |
Gemini 1.0 Pro |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
Gemini 1.0 Pro Vision |
✔ |
Gemini 1.0 Ultra |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
PaLM 2 for Text Unicorn |
|
PaLM 2 for Text |
✔ |
PaLM 2 for Chat |
✔ |
Codey for Code Chat, Codey for Code Completion |
✔ |
Embeddings for Text |
✔ |
Embeddings for Multimodal |
✔ |
Imagen for Captioning & VQA |
✔ |
Imagen (imagegeneration@002 ) |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
Imagen 2 (imagegeneration@006 ) |
✔ |
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
Chirp |
|
Vertex AI Search (Enterprise Search, Search for Healthcare) |
|
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
Agents |
|
South America
|
São Paulo, Brazil (southamerica-east1) |
Gemini 1.5 Pro |
✔ |
Gemini 1.5 Flash |
✔ |
Gemini 1.0 Pro |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
Gemini 1.0 Pro Vision |
✔ |
Gemini 1.0 Ultra |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
PaLM 2 for Text Unicorn |
|
PaLM 2 for Text |
|
PaLM 2 for Chat |
|
Codey for Code Chat, Codey for Code Completion |
|
Embeddings for Text |
✔ |
Embeddings for Multimodal |
✔ |
Imagen for Captioning & VQA |
|
Imagen (imagegeneration@002 ) |
|
Imagen 2 (imagegeneration@005 ) |
✔ |
Imagen 2 (imagegeneration@006 ) |
|
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
Chirp |
|
Vertex AI Search (Enterprise Search, Search for Healthcare) |
|
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
|
Agents |
|
Europe
|
EU Multi-region |
Netherlands (europe-west4) |
Paris, France (europe-west9) |
London, United Kingdom (europe-west2) |
Frankfurt, Germany (europe-west3) |
Belgium (europe-west1) |
Zürich, Switzerland (europe-west6) |
Madrid, Spain (europe-southwest1) |
Milan, Italy (europe-west8) |
Finland (europe-north1) |
Warsaw, Poland (europe-central2) |
Gemini 1.5 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.5 Flash |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
PaLM 2 for Text Unicorn |
PaLM 2 for Text |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
PaLM 2 for Chat |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Codey for Code Chat, Codey for Code Completion |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Embeddings for Text |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Embeddings for Multimodal |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen for Captioning & VQA |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen (imagegeneration@002 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 2 (imagegeneration@006 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Chirp |
✔ |
✔ |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
✔ |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
|
|
✔ |
✔ |
✔ |
Agents |
✔ |
Asia Pacific
|
Tokyo, Japan (asia-northeast1) |
Sydney, Australia (australia-southeast1) |
Singapore (asia-southeast1) |
Seoul, Korea (asia-northeast3) |
Taiwan (asia-east1) |
Hong Kong, China (asia-east2) |
Mumbai, India (asia-south1) |
Gemini 1.5 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.5 Flash |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Pro Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
PaLM 2 for Text Unicorn |
PaLM 2 for Text |
✔ |
|
✔ |
✔ |
PaLM 2 for Chat |
✔ |
|
✔ |
✔ |
Codey for Code Chat, Codey for Code Completion |
✔ |
|
✔ |
✔ |
Embeddings for Text |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Embeddings for Multimodal |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen for Captioning & VQA |
✔ |
|
✔ |
✔ |
Imagen (imagegeneration@002 ) |
✔ |
|
✔ |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 2 (imagegeneration@006 ) |
✔ |
|
✔ |
✔ |
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
✔ |
Chirp |
|
|
✔ |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
✔ |
✔ |
|
|
|
✔ |
Agents |
Middle East
|
Dammam, Saudi Arabia (me-central2) |
Doha, Qatar (me-central1) |
Tel Aviv, Israel (me-west1) |
Gemini 1.5 Pro |
✔ |
✔ |
✔ |
Gemini 1.5 Flash |
✔ |
✔ |
✔ |
Gemini 1.0 Pro |
✔ |
✔ |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
✔ |
✔ |
Gemini 1.0 Pro Vision |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra |
✔ |
✔ |
✔ |
Gemini 1.0 Ultra Vision |
✔ |
✔ |
✔ |
PaLM 2 for Text Unicorn |
PaLM 2 for Text |
PaLM 2 for Chat |
Codey for Code Chat, Codey for Code Completion |
Embeddings for Text |
✔ |
✔ |
✔ |
Embeddings for Multimodal |
✔ |
✔ |
✔ |
Imagen for Captioning & VQA |
Imagen (imagegeneration@002 ) |
Imagen 2 (imagegeneration@005 ) |
✔ |
✔ |
✔ |
Imagen 2 (imagegeneration@006 ) |
Imagen 3 (imagen-3.0-generate-001 ) |
✔ |
✔ |
✔ |
Imagen 3 Fast (imagen-3.0-fast-generate-001 ) |
✔ |
✔ |
✔ |
Chirp |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
Agents |
Google Cloud partner models
United States
|
Multi-region |
Columbus, Ohio (us-east5) |
Dallas, Texas (us-south1) |
Iowa (us-central1) |
Las Vegas, Nevada (us-west4) |
Moncks Corner, South Carolina (us-east1) |
Northern Virginia (us-east4) |
Oregon (us-west1) |
Anthropic Claude 3.5 Sonnet |
✔ |
✔ |
Anthropic Claude 3 Opus |
✔ |
✔ |
Anthropic Claude 3 Sonnet |
✔ |
✔ |
|
✔ |
Anthropic Claude 3 Haiku |
✔ |
✔ |
|
✔ |
Llama 3.1 405B (Preview) |
✔ |
|
|
✔ |
|
|
|
✔ |
Llama 3 70B |
✔ |
|
|
✔ |
Llama 3 8B |
✔ |
|
|
✔ |
Mistral Large (2407) |
✔ |
Mistral Nemo |
✔ |
Codestral |
✔ |
Jamba 1.5 Large (Preview) |
✔ |
Jamba 1.5 Mini (Preview) |
✔ |
Europe
|
EU Multi-region |
Netherlands (europe-west4) |
Belgium (europe-west1) |
Anthropic Claude 3.5 Sonnet |
✔ |
|
✔ |
Anthropic Claude 3 Opus |
|
Anthropic Claude 3 Sonnet |
|
Anthropic Claude 3 Haiku |
✔ |
✔ |
✔ |
Llama 3.1 405B (Preview) |
|
Llama 3 70B |
Llama 3 8B |
Mistral Large (2407) |
✔ |
✔ |
Mistral Nemo |
✔ |
✔ |
Codestral |
✔ |
✔ |
Jamba 1.5 Large (Preview) |
✔ |
✔ |
Jamba 1.5 Mini (Preview) |
✔ |
✔ |
Asia Pacific
|
Singapore (asia-southeast1) |
Anthropic Claude 3.5 Sonnet |
Anthropic Claude 3 Opus |
Anthropic Claude 3 Sonnet |
✔ |
Anthropic Claude 3 Haiku |
Llama 3.1 405B (Preview) |
Llama 3 70B |
Llama 3 8B |
Mistral Large (2407) |
Mistral Nemo |
Codestral |
Jamba 1.5 Large (Preview) |
Jamba 1.5 Mini (Preview) |
ML processing
Machine learning (ML) processing for Generative AI on Vertex AI
services occurs within the specific multi-region
when requests are made to regionally-available APIs in that multi-region.
United States
|
Multi-region |
Gemini 1.5 Pro |
✔ |
Gemini 1.5 Flash |
✔ |
Gemini 1.0 Pro |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
Gemini 1.0 Pro Vision |
✔ |
Embeddings for Multimodal |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
Chirp |
✔ |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
✔ |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
Agents |
✔ |
Canada
|
Montréal (northamerica-northeast1) |
Gemini 1.5 Pro |
✔ |
Gemini 1.5 Flash |
✔ |
Gemini 1.0 Pro |
Tuning for Gemini 1.0 Pro |
Gemini 1.0 Pro Vision |
Embeddings for Multimodal |
Imagen 2 (imagegeneration@005 ) |
Chirp |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
Agents |
Europe
|
EU Multi-region |
London, United Kingdom (europe-west2) |
Frankfurt, Germany (europe-west3) |
Gemini 1.5 Pro |
✔ |
Gemini 1.5 Flash |
✔ |
Gemini 1.0 Pro |
✔ |
Tuning for Gemini 1.0 Pro |
✔ |
Gemini 1.0 Pro Vision |
✔ |
Embeddings for Multimodal |
✔ |
Imagen 2 (imagegeneration@005 ) |
✔ |
Chirp |
✔ |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
✔ |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
✔ |
✔ |
Agents |
✔ |
Asia Pacific
|
Tokyo, Japan (asia-northeast1) |
Sydney, Australia (australia-southeast1) |
Mumbai, India (asia-south1) |
Gemini 1.5 Pro |
Gemini 1.5 Flash |
Gemini 1.0 Pro |
Tuning for Gemini 1.0 Pro |
Gemini 1.0 Pro Vision |
Embeddings for Multimodal |
Imagen 2 (imagegeneration@005 ) |
Chirp |
Vertex AI Search (Enterprise Search, Search for Healthcare) |
Dialogflow CX (Chat only and without the use of data stores or intent suggestions) |
✔ |
✔ |
✔ |
Agents |
Google Cloud partner models
United States
|
Multi-region |
Anthropic Claude 3.5 Sonnet |
✔ |
Anthropic Claude 3 Opus |
✔ |
Anthropic Claude 3 Sonnet |
✔ |
Anthropic Claude 3 Haiku |
✔ |
Llama 3.1 405B (Preview) |
✔ |
Llama 3 70B |
Llama 3 8B |
Mistral Large (2407) |
✔ |
Mistral Nemo |
✔ |
Codestral |
✔ |
Jamba 1.5 Large (Preview) |
✔ |
Jamba 1.5 Mini (Preview) |
✔ |
Europe
|
EU Multi-region |
Belgium (europe-west1) |
Netherlands (europe-west4) |
Anthropic Claude 3.5 Sonnet |
✔ |
✔ |
Anthropic Claude 3 Opus |
|
Anthropic Claude 3 Sonnet |
Anthropic Claude 3 Haiku |
✔ |
|
✔ |
Llama 3.1 405B (Preview) |
Llama 3 70B |
Llama 3 8B |
Mistral Large (2407) |
✔ |
|
✔ |
Mistral Nemo |
✔ |
|
✔ |
Codestral |
✔ |
|
✔ |
Jamba 1.5 Large (Preview) |
✔ |
|
✔ |
Jamba 1.5 Mini (Preview) |
✔ |
|
✔ |
Asia Pacific
|
Singapore (asia-southeast1) |
Anthropic Claude 3.5 Sonnet |
Anthropic Claude 3 Opus |
|
Anthropic Claude 3 Sonnet |
✔ |
Anthropic Claude 3 Haiku |
Llama 3.1 405B (Preview) |
|
Llama 3 70B |
✔ |
Llama 3 8B |
✔ |
Mistral Large (2407) |
Mistral Nemo |
Codestral |
Jamba 1.5 Large (Preview) |
Jamba 1.5 Mini (Preview) |
What's next