Is GPT-OSS-20B or Mistral Small 3.2 cheaper?

GPT-OSS-20B is cheaper on output tokens ($1.80 vs $2.20 per 1M).

Which has the larger context window, GPT-OSS-20B or Mistral Small 3.2?

GPT-OSS-20B has the larger context window (128K tokens).

GPT-OSS-20B vs Mistral Small 3.2

GPT-OSS-20B is cheaper on output tokens, while GPT-OSS-20B offers a larger context window. Choose GPT-OSS-20B or Mistral Small 3.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-OSS-20B	Mistral Small 3.2
Provider	Regolo AI	Regolo AI
Input / 1M tokens	$0.40	$0.50
Output / 1M tokens	$1.80	$2.20
Context window	128K	120K
Parameters	21B	—
Open weights	Yes	No
Released	Mar 2026	Jan 2025

GPT-OSS-20B details →Mistral Small 3.2 details →

FAQ

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