Gemma 3 12B vs Ministral 3 8B 2512

Price, context window & benchmark comparison

Google

Gemma 3 12B

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

Ministral 3 8B 2512

Mistral AI
$0.15 / $0.15
Input / Output · per 1M tokens
Compare different models
Google
Mistral AI
Verdict: Gemma 3 12B is 2.0× cheaper than Ministral 3 8B 2512 on a typical 3:1 input/output mix. Ministral 3 8B 2512 scores higher on the Artificial Analysis Intelligence Index (5.5 vs 3.8). Ministral 3 8B 2512 has the larger context window (262K vs 131K).
Gemma 3 12BMinistral 3 8B 2512
Input price / 1M$0.05$0.15
Output price / 1M$0.15$0.15
Blended price (3:1)$0.075$0.15
Cached input / 1M$0.015
Context window131K262K
Max output16K210K
Intelligence index3.85.5
Coding index5.89.7
Providers3
Best provider uptime (30m)98.4%
Vision inputYesYes
ReasoningNoNo
Tool callingYesYes
Released2025-03-132025-12-02
Retirement

Cost calculator

FAQ

Which is cheaper, Gemma 3 12B or Ministral 3 8B 2512?

Gemma 3 12B is 2.0× cheaper than Ministral 3 8B 2512 on a typical 3:1 input/output mix.

Gemma 3 12B vs Ministral 3 8B 2512: which has a bigger context window?

Gemma 3 12B: 131,072 tokens. Ministral 3 8B 2512: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 3 12B ≈ $175.00, Ministral 3 8B 2512 ≈ $375.00.

More comparisons