Gemma 4 31B vs Ministral 3 8B 2512
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Ministral 3 8B 2512 is 2% cheaper than Gemma 4 31B on a typical 3:1 input/output mix.
| Gemma 4 31B | Ministral 3 8B 2512 | |
|---|---|---|
| Input price / 1M | $0.09 | $0.15 |
| Output price / 1M | $0.34 | $0.15 |
| Blended price (3:1) | $0.15 | $0.15 |
| Cached input / 1M | $0.05 | $0.015 |
| Context window | 262K | 262K |
| Max output | 16K | 210K |
| Intelligence index | — | 5.5 |
| Coding index | 43.4 | 9.7 |
| Providers | — | 3 |
| Best provider uptime (30m) | — | 98.8% |
| Vision input | Yes | Yes |
| Reasoning | Yes | No |
| Tool calling | Yes | Yes |
| Released | 2026-04-02 | 2025-12-02 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Gemma 4 31B or Ministral 3 8B 2512?
Ministral 3 8B 2512 is 2% cheaper than Gemma 4 31B on a typical 3:1 input/output mix.
Gemma 4 31B vs Ministral 3 8B 2512: which has a bigger context window?
Gemma 4 31B: 262,144 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 4 31B ≈ $350.00, Ministral 3 8B 2512 ≈ $375.00.
More comparisons
Gemma 4 31B vs GLM 5.3 PrimeGemma 4 31B vs Qwen3.8 Max PrimeGemma 4 31B vs Command A+Gemma 4 31B vs GPT-6 Luna ProGemma 4 31B vs GPT-6 LunaGemma 4 31B vs GPT-6 Sol ProGemma 4 31B vs GPT-6 SolGemma 4 31B vs Claude Opus 5.5Gemma 4 31B vs MiMo-V2.6-Pro-UltraSpeedGemma 4 31B vs MiMo-V2.6-FlashGemma 4 31B vs Grok 4.7Gemma 4 31B vs Qwen3.8 Omni FlashGemma 4 31B vs GLM 5.3 FlashXGemma 4 31B vs DeepSeek V4.1 FlashGemma 4 31B vs GPT-6 AstraGemma 4 31B vs GPT-6 Astra ProMinistral 3 8B 2512 vs GLM 5.3 PrimeMinistral 3 8B 2512 vs Qwen3.8 Max PrimeMinistral 3 8B 2512 vs Command A+Ministral 3 8B 2512 vs GPT-6 Luna ProMinistral 3 8B 2512 vs GPT-6 LunaMinistral 3 8B 2512 vs GPT-6 Sol ProMinistral 3 8B 2512 vs GPT-6 SolMinistral 3 8B 2512 vs Claude Opus 5.5