Is gpt-oss-20b or Claude Haiku 4.5 cheaper?

gpt-oss-20b is cheaper on output tokens ($0.45 vs $5.00 per 1M).

Which has the larger context window, gpt-oss-20b or Claude Haiku 4.5?

Claude Haiku 4.5 has the larger context window (200K tokens).

gpt-oss-20b vs Claude Haiku 4.5

gpt-oss-20b is cheaper on output tokens, while Claude Haiku 4.5 offers a larger context window. Choose gpt-oss-20b or Claude Haiku 4.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	gpt-oss-20b	Claude Haiku 4.5
Provider	DigitalOcean	DigitalOcean
Input / 1M tokens	$0.05	$1.00
Output / 1M tokens	$0.45	$5.00
Context window	131K	200K
Parameters	21B	—
Open weights	Yes	No
Released	Aug 2025	Oct 2025

gpt-oss-20b details →Claude Haiku 4.5 details →

FAQ

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