Gemma 4 31B
View website
Released April 2026, the largest Gemma 4 dense model at 30.7B parameters. Scores 89.2% on AIME 2026. Optimized for consumer GPUs. Open-weight under Apache 2.0.
At a glance
- Context window
- 256K tokens
- Knowledge cutoff
- Jan 2025
- Modalities
- Text Text Image Image Video Video → Text Text
Capabilities
Function calling
Function calling
Connect to external tools, APIs, and systems.
Structured output
Structured output
Return responses in structured formats like JSON.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
|
Google Cloud
|
Self-hosted | Self-hosted |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.