Is Qwen Plus 0728 (thinking) or gpt-oss-20b cheaper?

gpt-oss-20b is cheaper on output tokens ($0.14 vs $0.78 per 1M).

Which has the larger context window, Qwen Plus 0728 (thinking) or gpt-oss-20b?

Qwen Plus 0728 (thinking) has the larger context window (1M tokens).

Qwen Plus 0728 (thinking) vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while Qwen Plus 0728 (thinking) offers a larger context window. Choose Qwen Plus 0728 (thinking) or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen Plus 0728 (thinking)	gpt-oss-20b
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.26	$0.03
Output / 1M tokens	$0.78	$0.14
Context window	1M	131K
Parameters	—	21B
Open weights	No	Yes
Released	Sep 2025	Aug 2025

Qwen Plus 0728 (thinking) details →gpt-oss-20b details →

FAQ

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