Granite-4.0-H-Small API
About
Process massive datasets with Granite-4.0-H-Small, featuring an expansive 131K context window for long-document analysis. This model delivers cost-effective pricing at $0.06/1M input and $0.27/1M output tokens, native tool calling support, open weights architecture. Access Granite-4.0-H-Small via the watsonx.ai API with up to 131K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Limits
Context Window
131K
Tokens
Input Limit
131K
Tokens
Max Output
131K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.06
Output
$0.27
Frequently Asked Questions
Granite-4.0-H-Small by watsonx.ai costs $0.06 per 1M input tokens and $0.27 per 1M output tokens.
Model Details
API Integration
NPM Package
watsonx-ai-provider
Environment Variables
WATSONX_AI_APIKEY
WATSONX_AI_PROJECT_ID