Is gpt-oss-safeguard-120b or GLM-5.2 cheaper?

gpt-oss-safeguard-120b is cheaper on output tokens ($0.60 vs $5.25 per 1M).

Which has the larger context window, gpt-oss-safeguard-120b or GLM-5.2?

GLM-5.2 has the larger context window (384K tokens).

gpt-oss-safeguard-120b vs GLM-5.2

gpt-oss-safeguard-120b is cheaper on output tokens, while GLM-5.2 offers a larger context window. Choose gpt-oss-safeguard-120b or GLM-5.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	gpt-oss-safeguard-120b	GLM-5.2
Provider	Tinfoil	Tinfoil
Input / 1M tokens	$0.15	$1.50
Output / 1M tokens	$0.60	$5.25
Context window	131K	384K
Parameters	—	—
Open weights	Yes	Yes
Released	Oct 2025	Jun 2026

gpt-oss-safeguard-120b details →GLM-5.2 details →

FAQ

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