Mistral Small 31 24b Instruct vs Gemma 4 12B IT
Gemma 4 12B IT is cheaper on output tokens, while Mistral Small 31 24b Instruct offers a larger context window. Choose Mistral Small 31 24b Instruct or Gemma 4 12B IT based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Mistral Small 31 24b Instruct | Gemma 4 12B IT |
|---|---|---|
| Provider | NanoGPT | Pioneer |
| Input / 1M tokens | $0.10 | $0.25 |
| Output / 1M tokens | $0.30 | $0.25 |
| Context window | 128K | 33K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Apr 2025 | May 2026 |
| LMArena (Chatbot Arena) Elo score | 1277 | — |
| LMArena Vision Elo score | 1136 | — |
FAQ
Is Mistral Small 31 24b Instruct or Gemma 4 12B IT cheaper?
Gemma 4 12B IT is cheaper on output tokens ($0.25 vs $0.30 per 1M).
Which has the larger context window, Mistral Small 31 24b Instruct or Gemma 4 12B IT?
Mistral Small 31 24b Instruct has the larger context window (128K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.