How much does ibm-granite/granite-4.2-3b cost per 1M tokens?

ibm-granite/granite-4.2-3b costs $0.030 per 1M input tokens and $0.120 per 1M output tokens on the standard tier. Cached input is $0.007 per 1M.

What is ibm-granite/granite-4.2-3b's context window?

ibm-granite/granite-4.2-3b accepts up to 131,072 tokens in a single request.

Is there a cheaper DeepInfra model than ibm-granite/granite-4.2-3b?

Yes. mistralai/Mistral-Nemo-Instruct-2407 is $0.019 per 1M input tokens versus $0.030 for ibm-granite/granite-4.2-3b, with a 131,072 token context window.

Where does this ibm-granite/granite-4.2-3b price come from?

From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

ibm-granite/granite-4.2-3b pricing

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-thought. ibm-granite/granite-4.2-3b from DeepInfra costs $0.030 per 1M input tokens and $0.120 per 1M output tokens. Cached input is $0.007 per 1M. Context window 131,072 tokens.

API id ibm-granite/granite-4.2-3b · DeepInfra · source · updated 2026-09-25 · general-purpose

$0.030

Input / 1M tokens

$0.120

Output / 1M tokens

$0.007

Cached input / 1M

131K

Context window

ibm-granite/granite-4.2-3b specifications

Provider: DeepInfra
API id: ibm-granite/granite-4.2-3b
Model type: general-purpose
Context window: 131K tokens
Max output: not published
Currency: USD
Price source: Provider API
Last checked: 2026-09-25

What ibm-granite/granite-4.2-3b costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0001
Document summary	50,000	2,000	$0.0017
1M tokens in, 200K out	1,000,000	200,000	$0.05

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does ibm-granite/granite-4.2-3b cost per 1M tokens?: ibm-granite/granite-4.2-3b costs $0.030 per 1M input tokens and $0.120 per 1M output tokens on the standard tier. Cached input is $0.007 per 1M.
What is ibm-granite/granite-4.2-3b's context window?: ibm-granite/granite-4.2-3b accepts up to 131,072 tokens in a single request.
Is there a cheaper DeepInfra model than ibm-granite/granite-4.2-3b?: Yes. mistralai/Mistral-Nemo-Instruct-2407 is $0.019 per 1M input tokens versus $0.030 for ibm-granite/granite-4.2-3b, with a 131,072 token context window.
Where does this ibm-granite/granite-4.2-3b price come from?: From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Compare ibm-granite/granite-4.2-3b with another model →

Other DeepInfra models

See all DeepInfra pricing →