| Model | Released | Context | Input / 1M | Output / 1M | Providers | Weights |
|---|---|---|---|---|---|---|
| Gemma 4 12Bgoogle/gemma-4-12b-it | May 23, 2026 | 16.4K | $0.30Sail Research | $2.00Sail Research | 1 | Open |
| Gemma 4 31Bgoogle/gemma-4-31b-it | April 2, 2026 | 262K | $0.12Doubleword | $0.35Doubleword | 4 | Open |
| Gemma 4 31B NVFP4google/gemma-4-31b-it-nvfp4 | April 2, 2026 | 262K | $0.12Chutes | $0.37Chutes | 2 | Open |
Lowest listed price, USD per 1M tokens, as of November 5, 2026.
Gemma 4 12B, Gemma 4 31B and Gemma 4 31B NVFP4. Each one uses its catalog ID, such as "google/gemma-4-12b-it", with the OpenAI-compatible endpoint at https://api.routerplus.com/v1.
Gemma 4 31B, at $0.12 per million input tokens and $0.35 per million output tokens on Doubleword. Prices as of November 5, 2026.
Gemma 4 31B, served by 4 providers: DeepInfra, Novita AI, Sail Research and Doubleword.
Gemma 4 12B, released May 23, 2026, is the newest Gemma 4 model in the RouterPlus catalog.
