Is Qwen 3.5 397B A17B or GPT OSS 20B cheaper?

GPT OSS 20B is cheaper on output tokens ($0.14 vs $3.00 per 1M).

Which has the larger context window, Qwen 3.5 397B A17B or GPT OSS 20B?

Qwen 3.5 397B A17B has the larger context window (262K tokens).

Qwen 3.5 397B A17B vs GPT OSS 20B

GPT OSS 20B is cheaper on output tokens, while Qwen 3.5 397B A17B offers a larger context window. Choose Qwen 3.5 397B A17B or GPT OSS 20B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen 3.5 397B A17B	GPT OSS 20B
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.45	$0.03
Output / 1M tokens	$3.00	$0.14
Context window	262K	131K
Parameters	397B	21B
Open weights	Yes	Yes
Released	Feb 2026	Aug 2025

Qwen 3.5 397B A17B 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.