Qwen3 Next 80B A3B Thinking

Same open weights, served by 1 provider.

alibabaOpen weights262k contextalibaba/qwen3-next-80b-a3b-thinking

Providers

Provider	Their model id	Serving	Input	Output	Cached in	Blended 3:1	Source
Alibaba Cloud Model Studio Original creator	`qwen3-next-80b-a3b-thinking`	standardQuantization not disclosedReduced context (131k of 262k)	$0.50	$6.0	—	$1.88	Unverified (via models.dev) Verified 3h ago · Changed 3h ago

Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.

Monthly cost estimate

Input tokens / month (M)Output tokens / month (M)Cache hit (% of input)

Alibaba Cloud Model Studio

$170/mo

Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.