Try Anthropic’s Claude models on Google Cloud’s Vertex AI 

Build production-ready AI applications and agents on a platform optimized for performance, trust, and global scale

Claude on Vertex AI overview

Try Claude Opus 4.6

Claude Opus 4.6: The latest version of Anthropic’s most intelligent model.

Claude Opus 4.6 is Anthropic’s most powerful model yet, excelling at coding, enterprise agents, and professional work.

Top use cases include coding, enterprise agents, professional work, financial analysis, and computer use.


Try Claude Opus 4.6

Claude Opus 4.6: The latest version of Anthropic’s most intelligent model.

Claude Opus 4.6 is Anthropic’s most powerful model yet, excelling at coding, enterprise agents, and professional work.

Top use cases include coding, enterprise agents, professional work, financial analysis, and computer use.


Try Claude Sonnet 4.6

Claude Sonnet 4.6: Anthropic’s frontier intelligence model for scale—built for coding, agents, and enterprise workflows.

Claude Sonnet 4.6 approaches Opus 4.6 intelligence at a lower cost, enabling high-quality task completion. It’s also Anthropic’s most advanced computer use model yet.

Top use cases include high-volume coding, data analysis, and content creation.



Try Claude Haiku 4.5

Claude Haiku 4.5: Anthropic’s most efficient model with a great combination of speed and price for parallelized work, sub-agents, and free-tier user experiences.

Claude Haiku 4.5 offers a great combination of performance, price, and speed among Anthropic models. Haiku 4.5 is designed for parallelized execution, sub-agents, and free-tier user experiences

Top use cases include latency-sensitive experiences like customer service agents, and sub-agents for coding, financial analysis, and research.


Replit & Anthropic: Empowering creators with Claude

How Replit is empowering the next billion creators with Claude on Vertex AI

Learn more about Claude on Vertex AI

Why Builders Choose Claude on Vertex AI

Rapidly build intelligent agents

Leverage the Vertex AI Agent Builder stack to move multi-step agentic workflows from prototype to scaled production.


Use Agent Engine to deploy and scale agents in a serverless environment. With Memory Bank and Sessions, your Claude-powered agents maintain persistent, long-term context across multiple interactions for a more natural user experience.


Maintain consistent performance during peak demand by reserving dedicated capacity at a fixed cost with Provisioned Throughput. To further improve efficiency, leverage features like the global endpoint for Claude, prompt caching with flexible Time To Live (TTL), batch predictions, web search, and a 1M token context window (preview).

Integrated governance controls keep agents on task and their actions logged. Secure the full AI stack including models and agents with Google Cloud’s foundational security and data residency controls, protect against novel AI threats like prompt injection and tool poisoning with Model Armor, and get advanced AI Protection in Security Command Center to prioritize AI risks and detect threats.

Vertex AI’s infrastructure is purpose-built to handle the compute demands of frontier models to help lower latency and improve efficiency.


Integrate your enterprise data with Claude's advanced capabilities, leveraging tools like BigQuery to extract valuable insights and drive informed decision-making.

The combination of Claude and Vertex AI helps us empower millions of merchants with our AI-enabled commerce assistant, Sidekick. There’s been a lot of merchants that we’ve talked to that say Sidekick ‘feels like a lifeline for small businesses’ and helps them ‘come out on top’.

Andrew McNamara, Director of Applied AI, Shopify

Shopify logo

Build with Claude on Vertex AI


Google Cloud