Is GPT OSS 20B or Mistral Small 4 cheaper?

GPT OSS 20B is cheaper on output tokens ($0.47 vs $0.63 per 1M).

Which has the larger context window, GPT OSS 20B or Mistral Small 4?

Mistral Small 4 has the larger context window (256K tokens).

GPT OSS 20B vs Mistral Small 4

GPT OSS 20B is cheaper on output tokens, while Mistral Small 4 offers a larger context window. Choose GPT OSS 20B or Mistral Small 4 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT OSS 20B	Mistral Small 4
Provider	LowRouter	LowRouter
Input / 1M tokens	$0.11	$0.16
Output / 1M tokens	$0.47	$0.63
Context window	131K	256K
Parameters	—	—
Open weights	Yes	Yes
Released	Aug 2025	Mar 2026

GPT OSS 20B details →Mistral Small 4 details →

FAQ

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