Gemma 4 31B
google/gemma-4-31b-it
- context
- 262K
- modalities
- image, text, video → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Low cost
Overview
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
- ChutesView Chutes
- CoreWeaveView CoreWeave
- CrusoeView Crusoe
- DeepInfraView DeepInfra
- FriendliView Friendli
- KTView KT
- ModalView Modal
- ModelRunView ModelRun
- NextBitView NextBit
- NovitaView Novita
- ParasailView Parasail
- PrimeIntellectView PrimeIntellect
- SambaNovaView SambaNova
- SiliconFlowView SiliconFlow
- VeniceView Venice
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Chutes | $0.12 | $0.37 |
| CoreWeave | $0.10 | $0.34 |
| Crusoe | $0.14 | $0.40 |
| DeepInfradeepinfra/fp8 · fp8 | $0.20 | $0.40 |
| DeepInfradeepinfra/fp8/flex · fp8 | $0.16 | $0.32 |
| DeepInfradeepinfra/fp8/priority · fp8 | $0.30 | $0.60 |
| DeepInfradeepinfra/turbo · fp4 | $0.135 | $0.51 |
| Friendli | $0.14 | $0.40 |
| KT | $0.10 | $0.34 |
| Modal | $0.34 | $0.10 |
| ModelRun | $0.75 | $1.00 |
| NextBit | $0.125 | $0.34 |
| Novita | $0.14 | $0.40 |
| Parasail | $0.15 | $0.40 |
| PrimeIntellect | $0.20 | $0.335 |
| SambaNova | $0.38 | $1.15 |
| SiliconFlow | $0.75 | $1.00 |
| Venice | $0.12 | $0.36 |
Chutes
- input / 1M
- $0.12
- output / 1M
- $0.37
CoreWeave
- input / 1M
- $0.10
- output / 1M
- $0.34
Crusoe
- input / 1M
- $0.14
- output / 1M
- $0.40
DeepInfra
deepinfra/fp8 · fp8
- input / 1M
- $0.20
- output / 1M
- $0.40
DeepInfra
deepinfra/fp8/flex · fp8
- input / 1M
- $0.16
- output / 1M
- $0.32
DeepInfra
deepinfra/fp8/priority · fp8
- input / 1M
- $0.30
- output / 1M
- $0.60
DeepInfra
deepinfra/turbo · fp4
- input / 1M
- $0.135
- output / 1M
- $0.51
Friendli
- input / 1M
- $0.14
- output / 1M
- $0.40
KT
- input / 1M
- $0.10
- output / 1M
- $0.34
Modal
- input / 1M
- $0.34
- output / 1M
- $0.10
ModelRun
- input / 1M
- $0.75
- output / 1M
- $1.00
NextBit
- input / 1M
- $0.125
- output / 1M
- $0.34
Novita
- input / 1M
- $0.14
- output / 1M
- $0.40
Parasail
- input / 1M
- $0.15
- output / 1M
- $0.40
PrimeIntellect
- input / 1M
- $0.20
- output / 1M
- $0.335
SambaNova
- input / 1M
- $0.38
- output / 1M
- $1.15
SiliconFlow
- input / 1M
- $0.75
- output / 1M
- $1.00
Venice
- input / 1M
- $0.12
- output / 1M
- $0.36
Use this model
through Nautili
Route requests to Gemma 4 31B through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.