How much does ibm-granite/granite-4.2-8b cost per 1M tokens?

ibm-granite/granite-4.2-8b costs $0.060 per 1M input tokens and $0.250 per 1M output tokens on the standard tier. Cached input is $0.015 per 1M.

What is ibm-granite/granite-4.2-8b's context window?

ibm-granite/granite-4.2-8b accepts up to 131,072 tokens in a single request.

Is there a cheaper DeepInfra model than ibm-granite/granite-4.2-8b?

Yes. mistralai/Mistral-Nemo-Instruct-2407 is $0.019 per 1M input tokens versus $0.060 for ibm-granite/granite-4.2-8b, with a 131,072 token context window.

Where does this ibm-granite/granite-4.2-8b 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-4.2-8b pricing

Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by leveraging built-in <think ...</think chain-of-thought. ibm-granite/granite-4.2-8b from DeepInfra costs $0.060 per 1M input tokens and $0.250 per 1M output tokens. Cached input is $0.015 per 1M. Context window 131,072 tokens.

API id ibm-granite/granite-4.2-8b · DeepInfra · source · updated 2026-09-25 · general-purpose

$0.060

Input / 1M tokens

$0.250

Output / 1M tokens

$0.015

Cached input / 1M

131K

Context window

ibm-granite/granite-4.2-8b specifications

Provider: DeepInfra
API id: ibm-granite/granite-4.2-8b
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-4.2-8b costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0002
Document summary	50,000	2,000	$0.0035
1M tokens in, 200K out	1,000,000	200,000	$0.11

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

ibm-granite/granite-4.2-8b price history

Recorded	Input /1M	Output /1M
2026-09-22	$0.060	$0.250
2026-09-21	$0.100	$0.150
2026-09-09	$0.060	$0.250
2026-09-01	$0.100	$0.150
2026-08-27	$0.060	$0.250

Common questions

How much does ibm-granite/granite-4.2-8b cost per 1M tokens?: ibm-granite/granite-4.2-8b costs $0.060 per 1M input tokens and $0.250 per 1M output tokens on the standard tier. Cached input is $0.015 per 1M.
What is ibm-granite/granite-4.2-8b's context window?: ibm-granite/granite-4.2-8b accepts up to 131,072 tokens in a single request.
Is there a cheaper DeepInfra model than ibm-granite/granite-4.2-8b?: Yes. mistralai/Mistral-Nemo-Instruct-2407 is $0.019 per 1M input tokens versus $0.060 for ibm-granite/granite-4.2-8b, with a 131,072 token context window.
Where does this ibm-granite/granite-4.2-8b 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-4.2-8b with another model →

Other DeepInfra models

See all DeepInfra pricing →