Claude Sonnet 4.5

Anthropic's mid-sized model for powering real-world agents, with capabilities in coding, computer use, cybersecurity, and working with office files like spreadsheets.

Try in Vertex AI View model card in Model Garden

Property	Description
Model ID	claude-sonnet-4-5@20250929
Token limits	Maximum input tokens 1M (Preview) 200,000 (GA) 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	July, 2025
Versions	claude-sonnet-4-5@20250929 Launch stage: Generally available Release date: September 29, 2025
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: 1,500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000 (beta), 200,000 (GA) europe-west1: QPM: 1,800 Input TPM: 1,800,000 uncached and cache write Output TPM: 180,000 Context length: 1,000,000 (beta), 200,000 (GA) asia-southeast1: QPM: 1,500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000 (beta), 200,000 (GA) global endpoint: QPM: 1,500 Input TPM: 1,500,000 uncached and cache write Output TPM: 150,000 Context length: 1,000,000 (beta), 200,000 (GA)
Pricing	See Pricing.