Claude Sonnet 4

Anthropic's mid-size model with superior intelligence for high-volume uses, such as coding, in-depth research, and agents.

Try in Vertex AI View model card in Model Garden

Property	Description
Model ID	claude-sonnet-4@20250514
Token limits	Maximum input tokens 200,000 Maximum output tokens 64,000
Capabilities	Batch predictions Supported Prompt caching Supported Function calling Supported Extended thinking Supported Count tokens Supported
Technical specifications
	Images	Limitation and specifications: See Vision in Anthropic's documentation
	Documents	Limitation and specifications: See PDF support in Anthropic's documentation
Knowledge cutoff date	March 2025
Versions	claude-sonnet-4@20250514 Launch stage: Generally available Release date: May 22, 2025
Supported regions
	Model availability (Includes fixed quota & Provisioned Throughput)	United States us-east5 Europe europe-west1 Asia pacific asia-east1 Global global endpoint
	ML processing	United States Multi-region Europe Multi-region Asia pacific asia-east1
Quota limits	us-east5: QPM: 35 Input TPM: 280,000 uncached and cache write Output TPM: 20,000 Context length: 200,000 europe-west1: QPM: 25 Input TPM: 180,000 uncached and cache write Output TPM: 20,000 Context length: 200,000 asia-east1: QPM: 70 Input TPM: 550,000 uncached and cache write Output TPM: 50,000 Context length: 200,000 global endpoint: QPM: 15 Input TPM: 130,000 uncached and cache write Output TPM: 10,000 Context length: 200,000
Pricing	See Pricing.