Is o4-mini-deep-research or GPT OSS 120B cheaper?

GPT OSS 120B is cheaper on output tokens ($0.15 vs $8.00 per 1M).

Which has the larger context window, o4-mini-deep-research or GPT OSS 120B?

o4-mini-deep-research has the larger context window (200K tokens).

o4-mini-deep-research vs GPT OSS 120B

GPT OSS 120B is cheaper on output tokens, while o4-mini-deep-research offers a larger context window. Choose o4-mini-deep-research or GPT OSS 120B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	o4-mini-deep-research	GPT OSS 120B
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$2.00	$0.03
Output / 1M tokens	$8.00	$0.15
Context window	200K	131K
Parameters	—	117B
Open weights	No	Yes
Released	Jun 2024	Aug 2025

o4-mini-deep-research details →GPT OSS 120B details →

FAQ

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