Gemma 4 31B (free)
LLM
by google ·
google-gemma-4-31b-it-20260402
Context window
262K
Max output
33K
Providers
12
Best input
Free
About this model
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...
Providers & prices
| Provider | Input $/MTok | Output $/MTok | Context | Upstream ID |
|---|---|---|---|---|
| G Google | Free | Free | 262K | google/gemma-4-31b-it:free |
| C CoreWeave | $0.1 | $0.34 | 262K | google/gemma-4-31b-it |
| V Venice | $0.12 | $0.36 | 256K | google/gemma-4-31b-it |
| C Chutes | $0.12 | $0.37 | 131K | google/gemma-4-31b-it |
| NA Novita AI | $0.14 | $0.4 | 262K | google/gemma-4-31b-it |
| C Crusoe | $0.14 | $0.4 | 262K | google/gemma-4-31b-it |
| F Friendli | $0.14 | $0.4 | 262K | google/gemma-4-31b-it |
| P Parasail | $0.15 | $0.4 | 262K | google/gemma-4-31b-it |
| D DeepInfra | $0.27 | $0.76 | 131K | google/gemma-4-31b-it |
| S SambaNova | $0.38 | $1.15 | 262K | google/gemma-4-31b-it |
| M ModelRun | $0.75 | $1.00 | 262K | google/gemma-4-31b-it |
| S SiliconFlow | $0.75 | $1.00 | 262K | google/gemma-4-31b-it |