Which Qwen model is cheapest on Amazon Bedrock?

Qwen3 Next 80B A3B at $0.140 per 1M input tokens in us-east-1, against $1.20 per 1M output tokens.

Which Qwen model is available in the most AWS regions?

Qwen3 32B (dense), callable in 11 of the 16 regions tracked here — 11 on-demand and 0 through a cross-region inference profile.

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

Cheapest

$0.140

per 1M input tokens

Widest availability

of 16 regions

Model	Context	Input	Output	Regions
Qwen3 235B A22B 2507 qwen.qwen3-235b-a22b-2507-v1:0	—	$0.220	$0.880	On-demand 8 Inference profile only 0
Qwen3 32B (dense) qwen.qwen3-32b-v1:0	—	$0.150	$0.600	On-demand 11 Inference profile only 0
Qwen3 Coder 480B A35B Instruct qwen.qwen3-coder-480b-a35b-v1:0	—	$0.450	$1.80	On-demand 7 Inference profile only 0
Qwen3 Coder Next qwen.qwen3-coder-next	—	$0.500	$1.20	On-demand 3 Inference profile only 0
Qwen3 Next 80B A3B qwen.qwen3-next-80b-a3b	—	$0.140	$1.20	On-demand 9 Inference profile only 0
Qwen3 VL 235B A22B qwen.qwen3-vl-235b-a22b	—	$0.530	$2.66	On-demand 9 Inference profile only 0
Qwen3-Coder-30B-A3B-Instruct qwen.qwen3-coder-30b-a3b-v1:0	—	$0.150	$0.600	On-demand 11 Inference profile only 0

Which Qwen model is cheapest on Amazon Bedrock?: Qwen3 Next 80B A3B at $0.140 per 1M input tokens in us-east-1, against $1.20 per 1M output tokens.
Which Qwen model is available in the most AWS regions?: Qwen3 32B (dense), callable in 11 of the 16 regions tracked here — 11 on-demand and 0 through a cross-region inference profile.