Google: Gemma 4 31B
google/gemma-4-31b-it-20260402Hugging Face ↗
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 usage over time
OpenRouter share of tokens, by day.
Google: Gemma 4 31B holds 0.49% today, up from 0.41% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
Google: Gemma 4 31B's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-07-14, Google: Gemma 4 31B holds 0.5% of OpenRouter token share, up 0.01pp over 30 days. Source: Tidelines (OpenRouter).
Where to run it
Providers & pricing
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| WandB | $0.12 | $0.35 | 262k | 99.80% |
| Venice | $0.12 | $0.36 | 256k | 99.52% |
| Chutes | $0.12 | $0.37 | 131k | 82.85% |
| DeepInfra · 262k | $0.12 | $0.37 | 262k | 99.23% |
| DeepInfra · 262k | $0.13 | $0.38 | 262k | 99.47% |
| SiliconFlow | $0.13 | $0.40 | 262k | 50.25% |
| Novita | $0.14 | $0.40 | 262k | 95.51% |
| Parasail | $0.15 | $0.40 | 262k | 90.31% |
| Phala | $0.15 | $0.46 | 262k | 73.96% |
| ModelRun | $0.22 | $0.55 | 262k | 100.00% |
| Together · 262k | $0.28 | $0.86 | 262k | 58.83% |
| Together · 262k | $0.39 | $0.97 | 262k | 99.39% |
| SambaNova | $0.38 | $1.15 | 131k | 99.97% |
| Cerebras | $0.99 | $1.49 | 131k | 79.27% |