Granite 4.0 Micro

ibm-granite/granite-4.0-h-micro

This model processes text and generates text. It has a context length of 131,000 tokens and is an open-weight model. Pricing is $0.017 per million input tokens and $0.112 per million output tokens.

  • structured outputs
  • open-weight

At a glance

provideribm-granite
releasedOct 2, 2025
context131K
input / M$0.017

Specifications

What the API gives you

Context window
131K tokens
Max output
118K tokens
Input price
$0.017 / 1M tokens
Output price
$0.11 / 1M tokens
Cache read
—
Modalities
text → text
Knowledge cutoff
—
Released
Oct 2, 2025

Measured evidence

Public benchmark record

GPQA Diamond (Epoch AI)
28.3% ± 1.82026-08-30evaluated 2026-08-30
OTIS Mock AIME (Epoch AI)
2.8% ± 1.42026-08-30evaluated 2026-08-30

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Math & ReasoningEstablished evidence

    16% of intended weighted task evidence across 2 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FrontierMath Tiers 1-3 (Epoch AI) or LiveBench Mathematics. 6 of 6 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.