Data residency

Data stored at rest in the customer selected location remains at rest in that location, independent of the Generative AI on Vertex AI endpoint called by that customer's request.

ML processing

Machine learning (ML) processing for Generative AI on Vertex AI services occurs within the specific region or multi-region where the request is made.

For any regional endpoint not explicitly listed in the following tables, such as those in the Middle East, there is no guarantee that ML processing occurs at a specific location. These endpoints support older models that do not offer ML processing guarantees.

ML processing for Google Cloud models

United States

Model name US multi-region
Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Gemini 2.5 Pro (gemini-2.5-pro)
Gemini 2.5 Flash (gemini-2.5-flash)
Gemini 2.0 Flash (gemini-2.0-flash)
Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite)
Tuning for Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Tuning for Gemini 2.5 Pro (gemini-2.5-pro)
Tuning for Gemini 2.5 Flash (gemini-2.5-flash)
Tuning for Gemini 2.0 Flash (gemini-2.0-flash-001)
Tuning for Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite-001)
Gemini 1.5 Flash (gemini-1.5-flash-002)
Gemini 1.5 Pro (gemini-1.5-pro-002)
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002)
Tuning for Gemini 1.5 Pro (gemini-1.5-pro-002)
Gemini Embeddings (gemini-embedding-001)
Embeddings for Text (text-embedding-004)
Embeddings for Text (text-embedding-005)
Embeddings for Text (text-multilingual-embedding-002)
Embeddings for Multimodal
Imagen 2 (imagegeneration@005)

Canada

Model name Montréal (northamerica-northeast1)
Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Gemini 2.5 Pro (gemini-2.5-pro)
Gemini 2.5 Flash , 1M only (gemini-2.5-flash)
Gemini 2.0 Flash (gemini-2.0-flash)
Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite)
Gemini 1.5 Pro (gemini-1.5-pro-002, 32k only)
Gemini 1.5 Flash (gemini-1.5-flash-002, 32k only)
Tuning for Gemini 1.5 Pro (gemini-1.0-pro-002)
Tuning for Gemini 1.5 Flash (gemini-1.5-flash-002)
Gemini Embeddings (gemini-embedding-001)
Embeddings for Text (text-embedding-004)
Embeddings for Text (text-embedding-005)
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 2.5 Flash, 1M only (gemini-2.5-flash)
Gemini 2.5 Flash, 128k only (gemini-2.5-flash)
Tuning for Gemini 2.5 Flash (gemini-2.5-flash)
Gemini 2.5 Pro (gemini-2.5-pro)
Tuning for Gemini 2.5 Pro (gemini-2.5-pro)
Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Tuning for Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Gemini 2.0 Flash (gemini-2.0-flash-001)
Tuning for Gemini 2.0 Flash (gemini-2.0-flash-001)
Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite-001)
Tuning for Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite-001)
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 Flash (gemini-1.5-flash-002)
Gemini Embeddings (gemini-embedding-001)
Embeddings for Text (text-embedding-004)
Embeddings for Text (text-embedding-005)
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) Singapore (asia-southeast1) Seoul, Korea (asia-northeast3)
Gemini 2.5 Flash, 1M only (gemini-2.5-flash)
Gemini 2.5 Flash, 128k only (gemini-2.5-flash)
Gemini 2.5 Pro (gemini-2.5-pro)
Gemini 2.5 Flash-Lite (gemini-2.5-flash-lite)
Gemini 2.0 Flash (gemini-2.0-flash-001)
Gemini 2.0 Flash-Lite (gemini-2.0-flash-lite-001)
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 Flash (gemini-1.5-flash-002)
Gemini Embeddings (gemini-embedding-001)
Embeddings for Text (text-embedding-004)
Embeddings for Text (text-embedding-005)
Embeddings for Text (text-multilingual-embedding-002)
Embeddings for Multimodal
Imagen 2 (imagegeneration@005)

ML processing for Google Cloud partner models

United States

US multi-region
Anthropic's Claude Opus 4.1
Anthropic's Claude Opus 4
Anthropic's Claude Sonnet 4
Anthropic's Claude 3.7 Sonnet
Anthropic's Claude 3.5 Haiku
Anthropic's Claude 3 Haiku
DeepSeek-V3.1
DeepSeek R1 (0528)
Llama 4 Maverick 17B-128E (Preview)
Llama 4 Scout 17B-16E (Preview)
Llama 3.3 70B (Preview)
Llama 3.2 90B (Preview)
Llama 3.1 405B
Llama 3.1 70B (Preview)
Llama 3.1 8B (Preview)
Mistral OCR (25.05)
Mistral Small 3.1 (25.03)
Mistral Large
Codestral

Europe

EU multi-region Belgium (europe-west1) Netherlands (europe-west4)
Anthropic's Claude Opus 4.1
Anthropic's Claude Opus 4
Anthropic's Claude Sonnet 4
Anthropic's Claude 3.7 Sonnet
Anthropic's Claude 3.5 Haiku
Anthropic's Claude 3 Haiku
DeepSeek-V3.1
DeepSeek R1 (0528)
Llama 4 Maverick 17B-128E (Preview)
Llama 4 Scout 17B-16E (Preview)
Llama 3.3 70B (Preview)
Llama 3.2 90B (Preview)
Llama 3.1 405B
Llama 3.1 70B (Preview)
Llama 3.1 8B (Preview)
Mistral OCR (25.05)
Mistral Small 3.1 (25.03)
Mistral Large
Codestral

Asia Pacific

Singapore (asia-southeast1) Taiwan (asia-east1)
Anthropic's Claude Opus 4.1
Anthropic's Claude Opus 4
Anthropic's Claude Sonnet 4
Anthropic's Claude 3.7 Sonnet
Anthropic's Claude 3.5 Haiku
Anthropic's Claude 3 Opus
Anthropic's Claude 3 Haiku
DeepSeek-V3.1
DeepSeek R1 (0528)
Llama 4 Maverick 17B-128E (Preview)
Llama 4 Scout 17B-16E (Preview)
Llama 3.3 70B (Preview)
Llama 3.2 90B (Preview)
Llama 3.1 405B
Llama 3.1 70B (Preview)
Llama 3.1 8B (Preview)
Mistral OCR (25.05)
Mistral Small 3.1 (25.03)
Mistral Large
Codestral

What's next