Is Devstral Small 2505 or GPT-OSS 20B cheaper?

GPT-OSS 20B is cheaper on output tokens ($0.14 vs $0.22 per 1M).

Which has the larger context window, Devstral Small 2505 or GPT-OSS 20B?

Devstral Small 2505 has the larger context window (128K tokens).

Devstral Small 2505 vs GPT-OSS 20B

GPT-OSS 20B is cheaper on output tokens, while Devstral Small 2505 offers a larger context window. Choose Devstral Small 2505 or GPT-OSS 20B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Devstral Small 2505	GPT-OSS 20B
Provider	IO.NET	IO.NET
Input / 1M tokens	$0.05	$0.03
Output / 1M tokens	$0.22	$0.14
Context window	128K	64K
Parameters	—	21B
Open weights	No	Yes
Released	May 2025	Dec 2024

Devstral Small 2505 details →GPT-OSS 20B details →

FAQ

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