Is Qwen2.5-Math 72B Instruct or QwQ 32B cheaper?

QwQ 32B is cheaper on output tokens ($0.86 vs $1.72 per 1M).

Which has the larger context window, Qwen2.5-Math 72B Instruct or QwQ 32B?

QwQ 32B has the larger context window (131K tokens).

Qwen2.5-Math 72B Instruct vs QwQ 32B

QwQ 32B is cheaper on output tokens, while QwQ 32B offers a larger context window. Choose Qwen2.5-Math 72B Instruct or QwQ 32B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen2.5-Math 72B Instruct	QwQ 32B
Provider	Alibaba (China)	Alibaba (China)
Input / 1M tokens	$0.57	$0.29
Output / 1M tokens	$1.72	$0.86
Context window	4K	131K
Parameters	—	33B
Open weights	Yes	Yes
Released	Sep 2024	Dec 2024

Qwen2.5-Math 72B Instruct details →QwQ 32B details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.