modelbenchmark.io

Granite-4.0-H-Small

IBM · granite-4-h-small

Compare

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads

Specification

watsonx listing

Context
131K
Max output
131K
Released
2025-10-02
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · watsonx list price

Input
$0.0636
Output
$0.265

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
watsonxvendor$0.0636$0.265131K131K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02watsonxInput$0.0636
2026-09-06watsonxInput$0.0636
2026-09-02watsonxOutput$0.265
2026-09-06watsonxOutput$0.265

More from IBM

most-hosted first