Claude Sonnet 5 on Google Cloud

Claude Sonnet 5 on Google Cloud is built for coding, agents, and professional work at scale.

Retirement Date: Not sooner than December 24, 2026.

• Agents: Claude Sonnet 5 on Google Cloud can operate as both a lead-agent and sub-agent in production pipelines, with reliable tool use and the cost profile to run high-volume agentic workloads at scale.
• Coding: Claude Sonnet 5 on Google Cloud is built for everyday development work: building features, refactoring, and debugging across complex codebases without losing quality.
• Enterprise workflows: Users need fewer rounds of editing to reach production-ready documents, spreadsheets, and presentations. Perfect for teams that need a reliable, everyday model for office tasks.
• Financial analysis: Claude Sonnet 5 on Google Cloud pairs general intelligence improvements with stronger analysis and spreadsheet work, fitting high-volume financial workflows where precision and iteration speed matter.
• Computer use: Claude Sonnet 5 on Google Cloud is our most efficient computer-use model, making browser automation cost-effective enough to deploy across business tools at scale.

Try in Agent Studio View model card in Model Garden

Model ID	claude-sonnet-5
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Image, PDF Outputs: Text
Token limits	Maximum input tokens: 1,000,000 Maximum output tokens: 128,000
Capabilities	Supported Computer use Web search Batch predictions Prompt caching Function calling Count tokens Memory tool Not supported
Usage types	Supported Shared Model Lineage Quota Provisioned Throughput Not supported
Technical specifications
	Images	Limitation and specifications: See Vision in Anthropic's documentation
	Documents	Limitation and specifications: See PDF support in Anthropic's documentation
Versions	claude-sonnet-5 Launch stage: Generally available Release date: June 30, 2026
Supported regions
	Model availability (Includes fixed quota & Provisioned Throughput)	United States Multi-region Europe Multi-region Global global endpoint
	ML processing	United States Multi-region Europe Multi-region Asia Pacific asia-southeast1
Quota limits	Multi-region: QPM: 1,250 Input TPM: 12,500,000 uncached and cache write Output TPM: 1,250,000 Context length: 1,000,000 Multi-region: QPM: 1,250 Input TPM: 12,500,000 uncached and cache write Output TPM: 1,250,000 Context length: 1,000,000 global endpoint: QPM: 2,500 Input TPM: 25,000,000 uncached and cache write Output TPM: 2,500,000 Context length: 1,000,000
Pricing	See Pricing.