Anthropic's most powerful model yet and the state-of-the-art coding model. Claude Opus 4.1 delivers sustained performance on long-running tasks that require focused effort and thousands of steps, significantly expanding what AI agents can solve.
Try in Vertex AI View model card in Model Garden
Property
Description
Model ID
claude-opus-4-1@20250805
Token limits
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
Versions
-
claude-opus-4-1@20250805 - Launch stage: Generally available
- Release date: August 5, 2025
Supported regions
Model availability
(Includes fixed quota & Provisioned Throughput)
United States
-
us-east5
Global
-
global endpoint
ML processing
United States
-
Multi-region
Quota limits
us-east5:
- QPM: 25
- Input TPM: 60,000 uncached and cache write
- Output TPM: 6,000
- Context length: 200,000
global endpoint:
- QPM: 25
- Input TPM: 60,000 uncached and cache write
- Output TPM: 6,000
- Context length: 200,000
Pricing
