Google: Gemma 4 31B
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...
Everything else
| Max output | 262K |
|---|---|
| Input / 1M | $0.1 |
| Output / 1M | $0.34 |
| Cache read / 1M | $0.1 |
| Cache write / 1M | — |
| 1M in + 1M out | $0.44 |
| Takes | image, text, video |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-04-02 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | google/gemma-4-31b-it |
Benchmarks
| source | epoch |
|---|---|
| eci | 141.86 |
| confidence | Likely |
| accessibility | Open weights (restricted use) |
| simpleQA | 0.096 |
| simpleQAStderr | 0.0094 |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.