EN
Open-weight models

Granite 4.2 8B: pricing, context and performance

Granite 4.2 8B in numbers: price per token, context window, independent benchmark scores and comparable models, based on public data checked on October 22, 2026.

Data as of October 22, 2026

Key figures

DeveloperIBM (Granite)
ReleasedAugust 25, 2026
Context window131,072 tokens (≈ 197 pages)
Maximum output117,964 tokens
Input price$0.06 per million tokens (median of 7 providers)
Output price$0.25 per million tokens
Open weightsYes
Reasoning modeYes
Tool callingYes
Structured output (JSON)No
Accepted inputstext
Providers offering it7

What you need to know

Released on August 25, 2026, Granite 4.2 8B is one of the 2 IBM (Granite) models tracked on this site. Its weights are published: you can download it and run it on your own servers, or use one of the 7 API providers that list it on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it 2 months old as of October 22, 2026.

We file it under open-weight models (68 models in this category on the site).

What do independent benchmarks say?

As of October 22, 2026, Epoch AI publishes no score for Granite 4.2 8B on our basket's benchmarks. To place it, rely on its specifications and price, then test it on your own cases.

Context and capabilities

Its context window reaches 131,072 tokens, roughly 197 pages of text at 500 words per page: enough for a medium-length document. A single answer can run to 117,964 tokens.

It accepts as input: text.

It can call tools (functions, APIs), which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (ibm-granite/granite-4.2-8b). See also our list of open-source models.

What it costs

Granite 4.2 8B costs $0.06 per million input tokens and $0.25 per million output tokens (median of 7 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.002; a thousand of those tasks, $1.7.

That is 4 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

What is it good for?

Given its category, Granite 4.2 8B is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to Granite 4.2 8B are:

Similar models

Other IBM (Granite) models

Frequently asked questions

How much does Granite 4.2 8B cost?

As of October 22, 2026, Granite 4.2 8B costs $0.06 per million input tokens and $0.25 per million output tokens (median of 7 providers). A task that reads 20,000 tokens and writes 2,000 costs about $0.002.

What is the context window of Granite 4.2 8B?

131,072 tokens, roughly 197 pages of text. An answer can reach 117,964 tokens.

Is Granite 4.2 8B open source?

Its weights are published: you can install it on your own servers. Check the license before commercial use.

When was Granite 4.2 8B released?

Granite 4.2 8B was released on August 25, 2026, according to models.dev.

Can you build an agent with Granite 4.2 8B?

Yes: it can call tools, the two basic building blocks of an agent.

Data sources

Data as of October 22, 2026

Report an error

Does a figure, a date or a fact look wrong? Tell us: every report is checked.