Granite 4.0 Micro: pricing, context and performance

Granite 4.0 Micro at a glance

IBM (Granite) released Granite 4.0 Micro on October 2, 2025. It has no declared reasoning mode: it answers directly, without an extra billed thinking step. Its weights are published: you can download it and run it on your own servers, or use one of the 2 API providers that list it on models.dev. That makes it more than a year old: successors may have shipped since.

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

Measured performance

Epoch AI publishes 2 results for Granite 4.0 Micro on our basket's benchmarks: too few to compute a reliable capability index.

• GPQA Diamond (PhD-level science questions): 28.3% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 2.8% — the best tracked model, GPT-5.5 Pro, reaches 100%

Technical specifications

Its context window reaches 131,000 tokens, roughly 197 pages of text at 500 words per page: enough for a medium-length document. A single answer can run to 131,000 tokens.

It accepts as input: text.

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

How much does Granite 4.0 Micro cost?

Granite 4.0 Micro costs $0.017 per million input tokens and $0.11 per million output tokens (median of 2 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.001; a thousand of those tasks, $0.56.

That is 8.9 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 4.0 Micro 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.

Comparable models

In the same category, the models closest to Granite 4.0 Micro are:

• LFM2-24B-A2B (Liquid AI, $0.12 per million output tokens)
• Ministral 3 3B 2512 (Mistral AI, $0.10 per million output tokens)
• DeepSeek R1 0528 Qwen3 8B (DeepSeek, $0.09 per million output tokens)
• Qwen3.5 9B (Alibaba Cloud (Qwen), index 49.6)