Gemma 4 12B Instruct is the instruction-tuned 12B model in Google DeepMind's Gemma 4 family of open models. It is a dense 11.95B-parameter multimodal model with configurable thinking modes, native function calling, and support for over 140 languages.
Modalities
In / out price
$0.30 / $2.00per 1M
Cached price
$0.15per 1M
Context
16K
Max output
16K
Providers
1 routeCompare providers by price, privacy, and speed.
Sail | Private | $0.30 | $2.00 | $0.15 | 16K | 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
2Streaming
Prompt caching
Uptime
FAQ
Common questions about Gemma 4 12B Instruct.