IBM

Granite-4.0-H-Small

CTX131K

Tools

Input$0.064/M

Output$0.27/M

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

Open weightsApache 2.0669/1044

Drag to turn

IBMTextCommon

Granite-4.0-H-Small

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

ibm/granite-4-h-small

Type: Text
Quality: Not rated yet
Context window: 131,072 tokens
Max output: 131,072 tokens
Input price: $0.064 / 1M tokens
Output price: $0.27 / 1M tokens
Cache read: —
Cache write: —
Parameters: 32B (32,207,337,984)
Downloads: 25K in the last 30 days
Likes: 310
Access to weights: Open download
Released: Oct 2, 2025
Knowledge cutoff: —
Takes in: Text
Puts out: Text
Reasoning: No
Tool calling: Yes
Structured output: Yes
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Common
Set number: 669/1044

Open IBM docs Weights on Hugging Face Where to run it 1 Meet its creature Battle MiMo-V2.6-Flash

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: www.ibm.com.

How good is it?

Public leaderboard scores for Granite-4.0-H-Small, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Granite-4.0-H-Small yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

1 provider sells Granite-4.0-H-Small through an API. Prices are per million tokens, cheapest first.

Cheapestwatsonx.ai$0.064 in · $0.27 out
From the labwatsonx.ai$0.064 in · $0.27 out

API providers

Provider	Input	Output	Context
watsonx.aiOfficial`ibm/granite-4-h-small`	$0.064	$0.27	131K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.