Gemma 3 4B vs Mistral Medium 3.1

Price, context window & benchmark comparison

G

Gemma 3 4B

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

Mistral Medium 3.1

Mistral AI
$0.40 / $2.00
Input / Output · per 1M tokens
Compare different models
G
M
Verdict: Gemma 3 4B is 12.8× cheaper than Mistral Medium 3.1 on a typical 3:1 input/output mix.
Gemma 3 4BMistral Medium 3.1
Input price / 1M$0.05$0.40
Output price / 1M$0.10$2.00
Blended price (3:1)$0.0625$0.80
Cached input / 1M$0.04
Context window131K131K
Max output16K105K
Intelligence index9.2
Coding index2.720.5
Providers
Best provider uptime (30m)
Vision inputYesYes
ReasoningNoNo
Tool callingNoYes
Released2025-03-132025-08-13
Retirement

Cost calculator

FAQ

Which is cheaper, Gemma 3 4B or Mistral Medium 3.1?

Gemma 3 4B is 12.8× cheaper than Mistral Medium 3.1 on a typical 3:1 input/output mix.

Gemma 3 4B vs Mistral Medium 3.1: which has a bigger context window?

Gemma 3 4B: 131,072 tokens. Mistral Medium 3.1: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemma 3 4B ≈ $150.00, Mistral Medium 3.1 ≈ $1,800.

More comparisons