Is GPT OSS 120B or Qwen 3.5 397B A17B cheaper?

GPT OSS 120B is cheaper on output tokens ($0.19 vs $3.00 per 1M).

Which has the larger context window, GPT OSS 120B or Qwen 3.5 397B A17B?

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

GPT OSS 120B vs Qwen 3.5 397B A17B

GPT OSS 120B is cheaper on output tokens, while Qwen 3.5 397B A17B offers a larger context window. Choose GPT OSS 120B or Qwen 3.5 397B A17B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT OSS 120B	Qwen 3.5 397B A17B
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.04	$0.45
Output / 1M tokens	$0.19	$3.00
Context window	131K	262K
Parameters	117B	397B
Open weights	Yes	Yes
Released	Aug 2025	Feb 2026

GPT OSS 120B details →Qwen 3.5 397B A17B details →

FAQ

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