Gemma 4 31B Instruct Turbo is a faster serving variant of Gemma 4 31B, the dense instruction-tuned model in Google DeepMind's open-weight Gemma 4 family. The base model takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Modalities
In / out price
$0.09 / $0.34per 1M
Cached price
$0.05per 1M
Context
262K
Max output
16K
Providers
1 routeCompare providers by price, privacy, and speed.
| Private | $0.09 | $0.34 | $0.05 | 262K | 16K | — | — |
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
6Streaming
Tool calling
Vision
video input
Reasoning
Prompt caching
Uptime
FAQ
Common questions about Gemma 4 31B Instruct Turbo.