Google Gemma 3 12B vs Mistral Ministral 3 8B 2512
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Gemma 3 12B is 2.0× cheaper at a typical mix of 3 input tokens per output token.
- Ministral 3 8B 2512 accepts longer prompts: 262K vs 131K tokens.
- Ministral 3 8B 2512 is the newer model (released 2025-12-02).
| Gemma 3 12B | Ministral 3 8B 2512 | |
|---|---|---|
| Vendor | Mistral | |
| Released | 2025-03-13 | 2025-12-02 |
| Input / 1M | $0.05 | $0.15 |
| Output / 1M | $0.15 | $0.15 |
| Cached input / 1M | — | $0.015 |
| Blended / 1M (3:1) | $0.075 | $0.15 |
| Context | 131K | 262K |
| Max output | 16K | 210K |
| Accepts | text, image | text, image |
| Reasoning | No | No |
| Providers on OpenRouter | 4 | 3 |
| Cheapest provider, output | $0.15 | $0.15 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
Gemma 3 12B
$5.25 per month$0.17 per day
Ministral 3 8B 2512
$11.25 per month$0.38 per day
Gemma 3 12B saves $6.00 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Gemma 3 12B with
Compare Ministral 3 8B 2512 with