Is Qwen 2.5 72B Instruct or GLM-5 cheaper?

Qwen 2.5 72B Instruct is cheaper on output tokens ($0.40 vs $3.20 per 1M).

Which has the larger context window, Qwen 2.5 72B Instruct or GLM-5?

GLM-5 has the larger context window (203K tokens).

Qwen 2.5 72B Instruct vs GLM-5

Qwen 2.5 72B Instruct is cheaper on output tokens, while GLM-5 offers a larger context window. Choose Qwen 2.5 72B Instruct or GLM-5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Qwen 2.5 72B Instruct	GLM-5
Provider	NovitaAI	NovitaAI
Input / 1M tokens	$0.38	$1.00
Output / 1M tokens	$0.40	$3.20
Context window	32K	203K
Parameters	—	744B
Open weights	Yes	Yes
Released	Oct 2024	Feb 2026

Qwen 2.5 72B Instruct details →GLM-5 details →

FAQ

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