Gemma 3 4B vs Ministral 3 14B 2512

Price, context window & benchmark comparison

G

Gemma 3 4B

Google
$0.05 / $0.10
Input / Output · per 1M tokens
VS
M

Ministral 3 14B 2512

Mistral AI
$0.20 / $0.20
Input / Output · per 1M tokens
Compare different models
G
M
Verdict: Gemma 3 4B is 3.2× cheaper than Ministral 3 14B 2512 on a typical 3:1 input/output mix. Ministral 3 14B 2512 has the larger context window (262K vs 131K).
Gemma 3 4BMinistral 3 14B 2512
Input price / 1M$0.05$0.20
Output price / 1M$0.10$0.20
Blended price (3:1)$0.0625$0.20
Cached input / 1M$0.02
Context window131K262K
Max output16K210K
Intelligence index6
Coding index2.714.4
Providers3
Best provider uptime (30m)99.7%
Vision inputYesYes
ReasoningNoNo
Tool callingNoYes
Released2025-03-132025-12-02
Retirement

Cost calculator

FAQ

Which is cheaper, Gemma 3 4B or Ministral 3 14B 2512?

Gemma 3 4B is 3.2× cheaper than Ministral 3 14B 2512 on a typical 3:1 input/output mix.

Gemma 3 4B vs Ministral 3 14B 2512: which has a bigger context window?

Gemma 3 4B: 131,072 tokens. Ministral 3 14B 2512: 262,144 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 3 4B ≈ $150.00, Ministral 3 14B 2512 ≈ $500.00.

More comparisons