Granite 4 Small H is IBM's language model with a 131K context window, starting at $0.0636 / 1M input and $0.265 / 1M output. A small-scale LLM from IBM's Granite 4 family with an H-suffix designation, balancing efficiency and instruction-following capability.
Specifications
Canonical IDibm-granite-4-small-h
TypeLanguage
StatusActive
CreatorIBMIBM
Providers
Context Window131K tokens
Input ModalitiesText
Output ModalitiesText
Benchmarks
Intelligence Index
#476
Math Index
#233
MMLU-Pro
#261
GPQA
#441
HLE
#501
LiveCodeBench
#250
IFBench
#354
Time to First Token
#575
SciCode
#432
AIME 2025
#233
LCR
#393
TerminalBench Hard
#327
TAU2
#351
Output TPS
#247

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
IBM watsonx logo
IBM watsonx
watsonx/ibm/granite-4-h-small
$0.0636$0.265

Cost Calculator

US Dollar ($)
Preset:

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Granite 4.2 8B—131K$0.060$0.150
Granite 4.1 8B—131K$0.050$0.100
Granite 4 Micro HMicro131K$0.017$0.112
Granite 4.2 30B——131K——
Granite 4.2 3B——131K——
Granite 4.1 30B—————
Granite 4.1 3B—————
Granite 4 MicroMicro————
Granite 4 Nano 1B HNano————
Granite 4 Nano 1BNano————

Model IDs

granite-4-0-h-small
ibm-granite-4-small-h
watsonx/ibm/granite-4-h-small