Is Qwen2.5-Math 72B Instruct or DeepSeek R1 cheaper?

Qwen2.5-Math 72B Instruct is cheaper on output tokens ($1.72 vs $2.29 per 1M).

Which has the larger context window, Qwen2.5-Math 72B Instruct or DeepSeek R1?

DeepSeek R1 has the larger context window (131K tokens).

Qwen2.5-Math 72B Instruct vs DeepSeek R1

Qwen2.5-Math 72B Instruct is cheaper on output tokens, while DeepSeek R1 offers a larger context window. Choose Qwen2.5-Math 72B Instruct or DeepSeek R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen2.5-Math 72B Instruct	DeepSeek R1
Provider	Alibaba (China)	Alibaba (China)
Input / 1M tokens	$0.57	$0.57
Output / 1M tokens	$1.72	$2.29
Context window	4K	131K
Parameters	—	671B
Open weights	Yes	No
Released	Sep 2024	Jan 2025

Qwen2.5-Math 72B Instruct details →DeepSeek R1 details →

FAQ

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