Granite 4.2 8B is out: what it costs and how to try it

In brief

Granite 4.2 8B is an IBM model released on August 31, 2026. You can use it in Whizi today at 1 credit per message on the Powerhouse plan and above, next to 280 plus other models on one login. List rates are $0.06 per million input tokens and $0.25 per million output tokens, with a 131K token context window.

What Granite 4.2 8B is

Granite 4.2 8B is an IBM model that went live on OpenRouter on August 31, 2026. It follows Granite 4.1 8B. Per standard answer it costs 1.8 times more, $0.0002 against $0.0001, and it keeps the same 131K token context window.

ReleasedAugust 31, 2026
ProviderIBM
Context window131K tokens
Input, per million tokens$0.06
Output, per million tokens$0.25
Credits per message in Whizi1
Minimum Whizi planPowerhouse

How to try Granite 4.2 8B in Whizi

Whizi puts Granite 4.2 8B in the same model picker as ChatGPT, Claude and Gemini, so there is no separate IBM account or API key to set up. Pick a plan on the pricing page, open a new chat, choose Granite 4.2 8B in the model picker and send your first message.

Each message costs 1 credit, whatever its length. If a question turns out to suit another model better, switch in the same conversation and the thread carries across. See switching models mid-conversation.

What Granite 4.2 8B costs

List rates are what the provider charges per token. The cost of one standard answer is the more useful number, because it prices the same unit of work across every model regardless of how each one is billed.

Input, per million tokens$0.06
Output, per million tokens$0.25
One standard answer$0.0002
One thousand answers$0.1850
Context window131K tokens
Credits per message in Whizi1
Minimum Whizi planPowerhouse
Rank by cost, of 113 priced models12

Prices are the published IBM rates as carried by OpenRouter, last refreshed 2026-09-26. The full dataset covering all 124 models from 33 providers is the AI model cost index, which is free to reuse with attribution.

What it costs inside Whizi

Whizi meters messages in credits rather than tokens, and Granite 4.2 8B is charged at 1 credit per message. The cost does not change with the length of your message or the length of the answer, so a one line question and a long document analysis cost the same.

PlanPrice per monthMonthly creditsMessages on this model
Powerhouse$49.99, or $34.99 billed yearly8,0008,000

Granite 4.2 8B is part of the Powerhouse catalogue. Anything not explicitly listed on the Starter or Pro tiers resolves to Powerhouse, which is the deliberate default for the frontier and specialist models. See plans and limits.

Workflow checklist
  • Input $0.06 and output $0.25 per million tokens
  • $0.0002 for one standard answer, $0.1850 for a thousand
  • 131K token context window
  • 1 credit per message inside Whizi
  • Requires the Powerhouse plan or above
  • Ranks 12 of 113 priced models by cost per answer
Common questions

Frequently asked questions

What is Granite 4.2 8B?

Granite 4.2 8B is an IBM model released on August 31, 2026, with a 131K token context window. It follows Granite 4.1 8B. Per standard answer it costs 1.8 times more, $0.0002 against $0.0001, and it keeps the same 131K token context window.

How do I use Granite 4.2 8B?

Sign up for Whizi, open a new chat and choose Granite 4.2 8B in the model picker. It is available on the Powerhouse plan and above at 1 credit per message, with no IBM account or API key needed.

How much does Granite 4.2 8B cost?

$0.06 per million input tokens and $0.25 per million output tokens at list rates, which works out to $0.0002 for one standard answer of 1,000 tokens in and 500 out, or $0.1850 for a thousand of them. Inside Whizi it is 1 credit per message on a monthly allowance, rather than metered per token.

Which Whizi plan includes Granite 4.2 8B?

Powerhouse and above, which is $49.99 per month or $34.99 billed yearly. At 1 credits per message, a Powerhouse allowance of 8,000 credits covers 8,000 messages on this model if you spend the whole allowance here, and most people mix in a 1 credit model for routine work so it goes further.