Anthropic's Claude on Google Cloud models

The Anthropic Claude models on Google Cloud offer fully managed and serverless models as APIs. To use a Claude model on Agent Platform, send a request directly to the Agent Platform API endpoint. Because the Anthropic Claude models use a managed API, there's no need to provision or manage infrastructure.

You can stream your Claude responses to reduce the end-user latency perception. A streamed response uses server-sent events (SSE) to incrementally stream the response.

You pay for Claude models as you use them (pay as you go), or you pay a fixed fee when using provisioned throughput. For pay-as-you-go pricing, see Anthropic Claude models on the Google Cloud pricing page.

Available Claude on Google Cloud models

The following models are available from Anthropic to use in Gemini Enterprise Agent Platform. To access a Claude on Google Cloud model, go to its Model Garden model card.

Anthropic's Claude models support Agent Platform request-response logging. Enable 30-day request-response logging of your prompt and completion activity to track any model misuse by your users. For more information, see Log requests and responses.

Claude Fable models

cognition Claude Fable 5.1 on Google Cloud Optimized for autonomous knowledge work and coding, handling long-running, complex, and asynchronous tasks.
cognition Claude Fable 5 on Google Cloud Optimized for autonomous knowledge work and coding, handling long-running, complex, and asynchronous tasks with agent harnesses.

Claude Opus models

Claude Opus 5.5 on Google Cloud Anthropic's most advanced Opus model, powering long-running agents while delivering improvements in coding and professional work.
Claude Opus 5 on Google Cloud A high-intelligence model from Anthropic, built for coding, agents, and professional work.
Claude Opus 4.8 on Google Cloud A high-intelligence Opus model built for coding and agents, featuring deep reasoning for enterprise workflows.
Claude Opus 4.7 on Google Cloud Optimized for coding, enterprise agents, UI design, and multi-day enterprise workflows.
Claude Opus 4.6 on Google Cloud Optimized for coding, enterprise agents, real-time operational workflows, and professional work.
Claude Opus 4.5 on Google Cloud Optimized for coding, agents, computer use, and sprawling enterprise workflows.
Claude Opus 4.1 on Google Cloud Industry leader for coding and agent capabilities, especially agentic search and complex problem solving.
Claude Opus 4 on Google Cloud State-of-the-art model for coding, agentic search, and long-horizon tasks requiring sustained reasoning.

Claude Sonnet models

Claude Sonnet 5 on Google Cloud Anthropic's most capable Sonnet model yet, built for coding, agents, and professional work at scale.
Claude Sonnet 4.6 on Google Cloud Delivers frontier intelligence at scale—built for coding, agents, cybersecurity, and enterprise workflows.
Claude Sonnet 4.5 on Google Cloud Built for powering real-world agents with strong capabilities across coding, computer use, and office files.
Claude Sonnet 4 on Google Cloud Balances impressive coding performance with the right speed and cost for high-volume use cases.

Claude Haiku models

Claude Haiku 4.5 on Google Cloud Near-frontier performance with the speed and cost efficiency to power free products and latency-sensitive experiences at scale.