Is Qwen3.5-122B or GPT-OSS-20B cheaper?

GPT-OSS-20B is cheaper on output tokens ($1.80 vs $3.60 per 1M).

Which has the larger context window, Qwen3.5-122B or GPT-OSS-20B?

Qwen3.5-122B has the larger context window (262K tokens).

Qwen3.5-122B vs GPT-OSS-20B

GPT-OSS-20B is cheaper on output tokens, while Qwen3.5-122B offers a larger context window. Choose Qwen3.5-122B or GPT-OSS-20B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen3.5-122B	GPT-OSS-20B
Provider	Regolo AI	Regolo AI
Input / 1M tokens	$0.90	$0.40
Output / 1M tokens	$3.60	$1.80
Context window	262K	128K
Parameters	—	21B
Open weights	Yes	Yes
Released	Feb 2026	Mar 2026

Qwen3.5-122B 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.