Granite 4 H Small

Granite 4 H Small is a text model from IBM watsonx with a context window of 20K tokens and max output of 20K tokens. Pricing starts at 0.06 per million input tokens and 0.25 per million output tokens.

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keywatsonx/ibm/granite-4-h-small
ProviderIBM watsonx
Provider IDwatsonx
ModeText
Canonical Namegranite-4-h-small
Context Window20K tokens
Max Output20K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0000600.060
Output Tokens0.0002500.250

Benchmarks

Intelligence Index10.8#177
Coding Index8.5#140
Math Index13.7#112
MMLU-Pro0.6#141
GPQA0.4#163
HLE0.0#194
LiveCodeBench0.3#132
IFBench0.3#132
Time to First Token8.66s#224
SciCode0.2#155
AIME 20250.1#112
LCR0.1#133
TerminalBench Hard0.0#124
TAU20.2#131