Is Codestral 2508 or gpt-oss-20b cheaper?

gpt-oss-20b is cheaper on output tokens ($0.14 vs $0.90 per 1M).

Which has the larger context window, Codestral 2508 or gpt-oss-20b?

Codestral 2508 has the larger context window (256K tokens).

Codestral 2508 vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while Codestral 2508 offers a larger context window. Choose Codestral 2508 or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Codestral 2508	gpt-oss-20b
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.30	$0.03
Output / 1M tokens	$0.90	$0.14
Context window	256K	131K
Parameters	—	21B
Open weights	No	Yes
Released	Aug 2025	Aug 2025

Codestral 2508 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.