Model
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| CoreWeavecoreweave/fp4 | fp4 | $0.10 | $0.34 |
| Venicevenice/fp4 | fp4 | $0.12 | $0.36 |
| Chuteschutes/fp4 | fp4 | $0.12 | $0.37 |
| DeepInfradeepinfra/turbo | fp4 | $0.135 | $0.51 |
| Crusoecrusoe/bf16 | bf16 | $0.14 | $0.40 |
| Friendlifriendli | — | $0.14 | $0.40 |
| Novitanovita/bf16 | bf16 | $0.14 | $0.40 |
| Parasailparasail/fp8 | fp8 | $0.15 | $0.40 |
| DeepInfradeepinfra/fp8/flex | fp8 | $0.16 | $0.32 |
| DeepInfradeepinfra/fp8 | fp8 | $0.20 | $0.40 |
| DeepInfradeepinfra/fp8/priority | fp8 | $0.30 | $0.60 |
| Io Netio-net | — | $0.361 | $1.0925 |
| SambaNovasambanova | — | $0.38 | $1.15 |
| ModelRunmodelrun/fp4 | fp4 | $0.75 | $1.00 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.75 | $1.00 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.