WhichAI / Models / Granite 4.0 Micro

Granite 4.0 Micro

· verified October 13, 2026

public paid api open-weights local

Provider

Statuspublic

AA Intelligence Index5.1 (official, read October 13, 2026)

Released2025-10-20

Context window131K

ModalitiesText

API price $/1M (in / out)$0.017 / $0.112 (OpenRouter)

Speedn/a

AccessAPI $0.017/$0.112 per 1M tokens on OpenRouter · open weights · listed October 20, 2025

In one line

Granite 4.0 Micro by IBM, measured by Artificial Analysis at 5.1 on the Intelligence Index. Added to WhichAI automatically from live data on October 13, 2026: no editorial review yet, so judge it by the numbers, not by a verdict. OpenRouter's description: “Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models.”

Alternatives worth a look

Ministral 3 3B 2512 (Mistral AI) · AA 4.8API $0.1/$0.1 per 1M tokens on OpenRouter · open weights · listed December 2, 2025
Ministral 3 8B 2512 (Mistral AI) · AA 5.5API $0.15/$0.15 per 1M tokens on OpenRouter · open weights · listed December 2, 2025
Phi-4 (Microsoft) · AA 5.9Open weights · laptop-friendly

Open Granite's official app ↗ Open in the WhichAI app Not sure? Take the 30-second finder

Artificial Analysis Intelligence Index, official scale (the number published on artificialanalysis.ai), relayed by OpenRouter and refreshed automatically: last read October 13, 2026. 210 models carry a current official measurement. A value marked ~ is converted from an earlier snapshot because no current measurement is published; an unmeasured model is never ranked. Context, price, modality and listing dates come from the public OpenRouter model list (refreshed automatically on the live site; static copy retrieved October 3, 2026) and vendor pages. Missing values are not published or not yet verified - shown as -. Sources are linked inside the app (the Ranking chapter and About > Methodology).