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
| 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-pro-002, gemini-1.5-pro-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| 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) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
Canada
| Montréal (northamerica-northeast1) | |
|---|---|
| Gemini 1.5 Pro ( gemini-1.5-pro-002, gemini-1.5-pro-001) |
✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ |
| 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) |
✔ |
South America
| São Paulo, Brazil (southamerica-east1) | |
|---|---|
| Gemini 1.5 Pro ( gemini-1.5-pro-002, gemini-1.5-pro-001) |
✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ |
| 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) |
✔ |
Europe
| 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-pro-002, gemini-1.5-pro-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| 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) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
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-pro-002, gemini-1.5-pro-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
| 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) |
✔ | ✔ | ✔ | ✔ | ✔ | ✔ | ✔ |
Middle East
| Dammam, Saudi Arabia (me-central2) | Doha, Qatar (me-central1) | Tel Aviv, Israel (me-west1) | |
|---|---|---|---|
| Gemini 1.5 Pro ( gemini-1.5-pro-002, gemini-1.5-pro-001) |
✔ | ✔ | ✔ |
| Gemini 1.5 Flash ( gemini-1.5-flash-002, gemini-1.5-flash-001) |
✔ | ✔ | ✔ |
| 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) |
✔ | ✔ | ✔ |
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's Claude 3.5 Sonnet | ✔ | ✔ | ||||||
| Anthropic's Claude 3 Opus | ✔ | ✔ | ||||||
| Anthropic's Claude 3 Sonnet | ✔ | ✔ | ✔ | |||||
| Anthropic's 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's Claude 3.5 Sonnet | ✔ | ✔ | |
| Anthropic's Claude 3 Opus | |||
| Anthropic's Claude 3 Sonnet | |||
| Anthropic's 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's Claude 3.5 Sonnet | |
| Anthropic's Claude 3 Opus | |
| Anthropic's Claude 3 Sonnet | ✔ |
| Anthropic's 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-pro-002) |
✔ |
Gemini 1.5 Pro (gemini-1.5-pro-001) |
✔ |
Gemini 1.5 Flash (gemini-1.5-flash-002) |
✔ |
Gemini 1.5 Flash (gemini-1.5-flash-001) |
✔ |
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-002) |
✔ |
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-001) |
✔ |
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002) |
✔ |
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-001) |
✔ |
| Gemini 1.0 Pro and Gemini 1.0 Pro Vision | ✔ |
| Tuning for Gemini 1.0 Pro | ✔ |
Embeddings for Text (text-embedding-004) |
✔ |
Embeddings for Text (text-multilingual-embedding-002) |
✔ |
| Embeddings for Multimodal | ✔ |
Imagen 2 (imagegeneration@005) |
✔ |
Canada
| Montréal (northamerica-northeast1) | |
|---|---|
Gemini 1.5 Pro (gemini-1.5-pro-002, 32k only) |
✔ |
Gemini 1.5 Pro (gemini-1.5-pro-001) |
✔ |
Gemini 1.5 Flash (gemini-1.5-flash-002, 32k only) |
✔ |
Gemini 1.5 Flash (gemini-1.5-flash-001) |
✔ |
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-002) |
✔ |
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-001) |
|
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002) |
✔ |
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-001) |
|
| Gemini 1.0 Pro and Gemini 1.0 Pro Vision | |
| Tuning for Gemini 1.0 Pro | |
Embeddings for Text (text-embedding-004) |
✔ |
Embeddings for Text (text-multilingual-embedding-002) |
✔ |
| Embeddings for Multimodal | |
Imagen 2 (imagegeneration@005) |
Europe
| EU Multi-region | London, United Kingdom (europe-west2) | Frankfurt, Germany (europe-west3) | |
|---|---|---|---|
Gemini 1.5 Pro (gemini-1.5-pro-002) |
✔ | ||
Gemini 1.5 Pro (gemini-1.5-pro-001) |
✔ | ||
Gemini 1.5 Flash (gemini-1.5-flash-002) |
✔ | ||
Gemini 1.5 Flash (gemini-1.5-flash-002, 32k only) |
✔ | ✔ | |
Gemini 1.5 Flash (gemini-1.5-flash-001) |
✔ | ||
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-002) |
✔ | ||
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-001) |
✔ | ||
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002) |
✔ | ||
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-001) |
✔ | ||
| Gemini 1.0 Pro and Gemini 1.0 Pro Vision | ✔ | ||
| Tuning for Gemini 1.0 Pro | ✔ | ||
Embeddings for Text (text-embedding-004) |
✔ | ✔ | |
Embeddings for Text (text-multilingual-embedding-002) |
✔ | ✔ | |
| Embeddings for Multimodal | ✔ | ||
Imagen 2 (imagegeneration@005) |
✔ |
Asia Pacific
| Tokyo, Japan (asia-northeast1) | Sydney, Australia (australia-southeast1) | Mumbai, India (asia-south1) | |
|---|---|---|---|
Gemini 1.5 Pro (gemini-1.5-pro-002) |
|||
Gemini 1.5 Pro (gemini-1.5-pro-001) |
|||
Gemini 1.5 Flash (gemini-1.5-flash-002, 32k only) |
✔ | ✔ | |
Gemini 1.5 Flash (gemini-1.5-flash-002, 128k only) |
✔ | ||
Gemini 1.5 Flash (gemini-1.5-flash-001) |
|||
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-002) |
|||
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-001) |
|||
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002) |
|||
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-001) |
|||
| Gemini 1.0 Pro and Gemini 1.0 Pro Vision | |||
| Tuning for Gemini 1.0 Pro | |||
Embeddings for Text (text-embedding-004) |
✔ | ||
Embeddings for Text (text-multilingual-embedding-002) |
✔ | ||
| Embeddings for Multimodal | |||
Imagen 2 (imagegeneration@005) |
Google Cloud partner models
United States
| Multi-region | |
|---|---|
| Anthropic's Claude 3.5 Sonnet | ✔ |
| Anthropic's Claude 3 Opus | ✔ |
| Anthropic's Claude 3 Sonnet | ✔ |
| Anthropic's 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's Claude 3.5 Sonnet | ✔ | ✔ | |
| Anthropic's Claude 3 Opus | |||
| Anthropic's Claude 3 Sonnet | |||
| Anthropic's 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's Claude 3.5 Sonnet | |
| Anthropic's Claude 3 Opus | |
| Anthropic's Claude 3 Sonnet | ✔ |
| Anthropic's 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
- Learn about Google Cloud regions.
Learn more about security controls by feature.
Learn about the models that provide Generative AI on Vertex AI support. See Generative AI foundational model reference.
Learn about Vertex AI locations.