Gemma 4 31B Instruct NVFP4 is a 4-bit NVFP4 quantization of Gemma 4 31B IT, Google DeepMind's 30.7B-parameter dense open model, with both weights and activations quantized. It supports text and image input, configurable thinking, and function calling.
Modalities
In / out price
$0.14 / $0.40per 1M
Cached price
$0.07per 1M
Context
261K
Max output
131K
Providers
1 routeCompare providers by price, privacy, and speed.
Sail | Private | $0.14 | $0.40 | $0.07 | 261K | 131K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
2Streaming
Prompt caching
Uptime
FAQ
Common questions about Gemma 4 31B Instruct NVFP4.