Claude Sonnet 4.6 on Google Cloud

Claude Sonnet 4.6 on Google Cloud delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows.

Retirement Date: Not sooner than February 17, 2027.

Try in Agent Studio View model card in Model Garden

Technical specifications
Model ID	`claude-sonnet-4-6`
Launch stage	GA
Supported inputs & outputs	Inputs: Text, Code, Images, Documents 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 Extended thinking Count tokens Not supported
Usage types	Supported Fixed quota Provisioned Throughput Not supported
	Images	Limitation and specifications: See Vision in Anthropic's documentation
	Documents	Limitation and specifications: See PDF support in Anthropic's documentation
Versions	`claude-sonnet-4-6` Launch stage: Generally available Release date: February 17, 2026
Supported regions
	Model availability (Includes fixed quota & Provisioned Throughput)	United States `us-east5` Europe `europe-west1` Asia Pacific `asia-southeast1` Global `global endpoint`
	ML processing	United States `Multi-region` Europe `Multi-region` Asia Pacific `asia-southeast1`
Quota limits	us-east5: QPM: 1500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000 europe-west1: QPM: 1800 Input TPM: 1,800,000 uncached and cache write Output TPM: 180,000 Context length: 1,000,000 asia-southeast1: QPM: 1500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000 global endpoint: QPM: 1500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000
Pricing	See Pricing.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-08-26 UTC.