Gemma 3 12B vs Granite 4.2 8B

Price, context window & benchmark comparison

G

Gemma 3 12B

Google
$0.05 / $0.15
Input / Output · per 1M tokens
VS
I

Granite 4.2 8B

IBM Granite
$0.06 / $0.25
Input / Output · per 1M tokens
Compare different models
G
I
Verdict: Gemma 3 12B is 30% cheaper than Granite 4.2 8B on a typical 3:1 input/output mix. Granite 4.2 8B scores higher on the Artificial Analysis Intelligence Index (11.1 vs 3.8).
Gemma 3 12BGranite 4.2 8B
Input price / 1M$0.05$0.06
Output price / 1M$0.15$0.25
Blended price (3:1)$0.075$0.11
Cached input / 1M$0.015
Context window131K131K
Max output16K118K
Intelligence index3.811.1
Coding index5.822.4
Providers
Best provider uptime (30m)
Vision inputYesNo
ReasoningNoYes
Tool callingYesYes
Released2025-03-132026-08-31
Retirement

Cost calculator

FAQ

Which is cheaper, Gemma 3 12B or Granite 4.2 8B?

Gemma 3 12B is 30% cheaper than Granite 4.2 8B on a typical 3:1 input/output mix.

Gemma 3 12B vs Granite 4.2 8B: which has a bigger context window?

Gemma 3 12B: 131,072 tokens. Granite 4.2 8B: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 3 12B ≈ $175.00, Granite 4.2 8B ≈ $245.00.

More comparisons