Which Google model is cheapest on Amazon Bedrock?

Gemma 3 4B IT at $0.040 per 1M input tokens in us-east-1, against $0.080 per 1M output tokens.

Which Google model is available in the most AWS regions?

Gemma 3 12B IT, callable in 9 of the 16 regions tracked here — 9 on-demand and 0 through a cross-region inference profile.

3 Google models available through Bedrock, with price per 1M tokens, context window and region coverage.

Cheapest

$0.040

per 1M input tokens

Widest availability

of 16 regions

Model	Context	Input	Output	Regions
Gemma 3 12B IT google.gemma-3-12b-it	—	$0.090	$0.290	On-demand 9 Inference profile only 0
Gemma 3 27B PT google.gemma-3-27b-it	—	$0.230	$0.380	On-demand 9 Inference profile only 0
Gemma 3 4B IT google.gemma-3-4b-it	—	$0.040	$0.080	On-demand 9 Inference profile only 0

Which Google model is cheapest on Amazon Bedrock?: Gemma 3 4B IT at $0.040 per 1M input tokens in us-east-1, against $0.080 per 1M output tokens.
Which Google model is available in the most AWS regions?: Gemma 3 12B IT, callable in 9 of the 16 regions tracked here — 9 on-demand and 0 through a cross-region inference profile.