Is GPT-OSS 120B or Qwen3-VL 235B cheaper?

GPT-OSS 120B is cheaper on output tokens ($0.71 vs $1.91 per 1M).

Which has the larger context window, GPT-OSS 120B or Qwen3-VL 235B?

Qwen3-VL 235B has the larger context window (218K tokens).

GPT-OSS 120B vs Qwen3-VL 235B

GPT-OSS 120B is cheaper on output tokens, while Qwen3-VL 235B offers a larger context window. Choose GPT-OSS 120B or Qwen3-VL 235B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-OSS 120B	Qwen3-VL 235B
Provider	STACKIT	STACKIT
Input / 1M tokens	$0.49	$1.64
Output / 1M tokens	$0.71	$1.91
Context window	131K	218K
Parameters	117B	—
Open weights	Yes	Yes
Released	Aug 2025	Nov 2024

GPT-OSS 120B details →Qwen3-VL 235B details →

FAQ

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