Base model

granite-4.2-3b

from $0.03 at 3 providers

ibm/granite-4-2-3b · 3B parameters · 3 providers · Text models ·

Price alerts

Found 3

Simple Full

Download

The offers of the current filter, current prices in USD.

Free for everyone, no sign-in needed: the whole catalog in one file, up to 20 downloads an hour (60 with a free account).

JSON CSV YAML Excel

The same as an API for bots (format=json|csv|yaml, limit, offset):

https://airatecard.com/export?format=json&model=ibm%2Fgranite-4-2-3b

API parameters and a form

Model	Variant	Provider	Input, $	Output, $	Your cost/mo, $	Subscription, $/mo	Region	Context	Max output	Accepts	Last checked
= granite-4.2-3b×		Provider deepinfra 1 edenai 1 huggingface 1				Pricing pay per use 3	Region US 1			Input text 2	Status Active 3
granite-4.2-3b granite-4.2-3b		deepinfra ↗	$0.03	$0.12	—			131K	—		4 Nov 12:00
granite-4.2-3b granite-4.2-3b	via DeepInfra	edenai ↗	$0.03	$0.12	—		US	131K	—	text	4 Nov 12:00
granite-4.2-3b granite-4.2-3b		huggingface ↗	$0.03	$0.12	—			131K	—	text	4 Nov 12:00

Ranges in one field: "from-to" - "0.5-3", "-3" (up to), "128k-" (from); a colon works too. Several ticked values of one column are ORed, columns are ANDed.

Input price history, $/1M

Latest: minimum $0.03, median $0.03 (Nov 4, 2026)

The GRANITE family - base models: 14

granite

About the model: cost of your workload, questions, comparisons, citation

Cost of my workload → in the Tools tab: every provider of this model, cheapest first

Frequently asked questions

How much does granite-4.2-3b API cost?

From $0.03 input and $0.12 output per 1M tokens, at deepinfra.

Which provider offers granite-4.2-3b cheapest?

deepinfra offers the lowest price, $0.03 per 1M tokens, among 3 providers.

What is the context window of granite-4.2-3b?

131K tokens.

Where is granite-4.2-3b available?

Available in: US.

Compare

vs Qwen 2.5 72B Instruct vs Qwen2.5-Coder-32B-Instruct vs Qwen3 14B

Source: AI Rate Card, https://airatecard.com/en/model/ibm/granite-4-2-3b, prices checked 2026-11-04