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
Model ID
claude-sonnet-4
Launch stage
GA
Supported inputs & outputs
- Inputs:
Text , Code , Images - Outputs:
Text
Token limits
- Maximum input tokens: 1M (Preview)
200,000 (GA) - Maximum output tokens: 64,000
Capabilities
- Supported
- Not supported
Usage types
- Supported
- 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
Knowledge cutoff date
March 2025
Versions
-
claude-sonnet-4 - Launch stage: Generally available
- Release date: May 22, 2025
- Retirement date not sooner than: May 14, 2026
Supported regions
Model availability
(Includes fixed quota & Provisioned Throughput)
- United States
-
us-east5 - Europe
-
europe-west1 - Global
-
global endpoint
ML processing
- United States
-
Multi-region - Europe
-
Multi-region
Quota limits
us-east5:
- QPM: 35
- Input TPM: 280,000 uncached and cache write
- Output TPM: 20,000
- Context length: 1,000,000
europe-west1:
- QPM: 25
- Input TPM: 180,000 uncached and cache write
- Output TPM: 20,000
- Context length: 1,000,000
global endpoint:
- QPM: 35
- Input TPM: 276,000 uncached and cache write
- Output TPM: 24,000
- Context length: 1,000,000
Pricing
