Is Claude 3 Haiku or gpt-oss-20b cheaper?

gpt-oss-20b is cheaper on output tokens ($0.14 vs $1.25 per 1M).

Which has the larger context window, Claude 3 Haiku or gpt-oss-20b?

Claude 3 Haiku has the larger context window (200K tokens).

Claude 3 Haiku vs gpt-oss-20b

gpt-oss-20b is cheaper on output tokens, while Claude 3 Haiku offers a larger context window. Choose Claude 3 Haiku or gpt-oss-20b based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Claude 3 Haiku	gpt-oss-20b
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.25	$0.03
Output / 1M tokens	$1.25	$0.14
Context window	200K	131K
Parameters	—	21B
Open weights	No	Yes
Released	Mar 2024	Aug 2025

Claude 3 Haiku 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.