Claude Haiku 4.5 delivers near-frontier performance for a wide range of use cases, and stands out as one of the best coding models in the world–with the right speed and cost to power free products and high-volume user experiences.
Try in Vertex AI View model card in Model Garden
Model ID
claude-haiku-4-5@20251001
Launch stage
GA
Supported inputs & outputs
- Inputs:
Image , PDF , Text - Outputs:
Text
Token limits
- Maximum input tokens: 200,000
- 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
Versions
-
claude-haiku-4-5@20251001 - Launch stage: Generally available
- Release date: October 15, 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: 1,500
- Context length: 200,000
europe-west1:
- QPM: 1,800
- Context length: 200,000
asia-east1:
- QPM: 2,500
- Context length: 200,000
global endpoint:
- QPM: 2,500
- Context length: 200,000
Pricing
