RentGPU RentGPU
Find a GPU →
by IBM Research

granite-4.2-3b.

text open weights 131K ctx
Cheapest input
$0.03/M
on DeepInfra
Cheapest output
$0.12/M
on DeepInfra
Hosted equiv.
~$0.04/hr
@ 100 tok/s on DeepInfra

Granite-4.2-3B is the compact reasoning model in the Granite 4.2 family. Despite its small parameter count, it delivers strong performance on reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-t

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $0.03 $0.12 Launch ↗
FAQ

Frequently asked.

How do I run granite-4.2-3b?
granite-4.2-3b is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access granite-4.2-3b?
granite-4.2-3b is available via DeepInfra. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run granite-4.2-3b?
API pricing starts at $0.03/M input tokens and $0.12/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is granite-4.2-3b open-source or proprietary?
granite-4.2-3b is open-weight under the license. You can download and self-host it.