Model
Gemma 4 31B IT
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
14 providersreleased Apr 2, 2026open weights
$0.08
best input /M · NanoGPT
$0.33
best output /M
262K
context window
33K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Nvidia google/gemma-4-31b-it | — | — | — | — | 256K | reasoningtoolsno structuredvision | Apr 2, 2026 | |
| NanoGPT google/gemma-4-31b-it | $0.08 | $0.33 | $0.04 | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Kilo Gateway google/gemma-4-31b-it | $0.08 | $0.35 | $0.01 | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| OpenRouter google/gemma-4-31b-it | $0.1 | $0.34 | $0.1 | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Lilac google/gemma-4-31b-it | $0.11 | $0.35 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| OrcaRouter google/gemma-4-31b-it | $0.13 | $0.38 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| FastRouter google/gemma-4-31b-it | $0.13 | $0.38 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Crusoe google/gemma-4-31b-it | $0.14 | $0.4 | $0.14 | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Merge Gateway google/gemma-4-31b-it | $0.14 | $0.4 | — | — | 262K | reasoningno toolsno structuredno vision | Apr 2, 2026 | |
| Vercel AI Gateway google/gemma-4-31b-it | $0.14 | $0.4 | — | — | 262K | no reasoningtoolsstructuredvision | Apr 2, 2026 | |
| NovitaAI google/gemma-4-31b-it | $0.14 | $0.4 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Abacus google/gemma-4-31b-it | $0.14 | $0.4 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| ai& google/gemma-4-31b-it | $0.2 | $0.5 | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 | |
| Google gemma-4-31b-it | — | — | — | — | 262K | reasoningtoolsstructuredvision | Apr 2, 2026 |
Price badge
https://models.sutraworks.ai/badge/google/gemma-4-31b-it.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- repricedvia nano-gpt · Aug 21, 2026
- input: $0.1 → $0.08
- output: $0.35 → $0.33
- cache_read: $0.05 → $0.04
Weights
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.