Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Google: Gemma 4 31B — Google. Context window 262,144 tokens. API pricing (per 1M tokens): Input $0.09, Output $0.34. License: Open-Weights. LMArena 1,443. GPQA Diamond 75.8%.
| Provider | |
|---|---|
| API model ID | google/gemma-4-31b-it |
| Tier | Frontier |
| Context window | 262,144 tokens |
| Max output | 16,384 tokens |
| License | Open-Weights |
| API pricing (per 1M tokens) · Input | $0.09 |
| API pricing (per 1M tokens) · Output | $0.34 |
| LMArena | 1,443 (gemma-4-31b) |
| GPQA Diamond | 75.8% |
LMArena (CC-BY 4.0, best reasoning setting, 2026-10-02) · GPQA Diamond: Epoch AI (CC-BY 4.0)
Compare in the full catalog