Is GLM 4.7 Thinking or GLM 4.5 cheaper?

GLM 4.7 Thinking is cheaper on output tokens ($0.80 vs $1.30 per 1M).

Which has the larger context window, GLM 4.7 Thinking or GLM 4.5?

GLM 4.7 Thinking has the larger context window (200K tokens).

GLM 4.7 Thinking vs GLM 4.5

GLM 4.7 Thinking is cheaper on output tokens, while GLM 4.7 Thinking offers a larger context window. Choose GLM 4.7 Thinking or GLM 4.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GLM 4.7 Thinking	GLM 4.5
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$0.20	$0.30
Output / 1M tokens	$0.80	$1.30
Context window	200K	128K
Parameters	—	355B
Open weights	No	No
Released	Dec 2025	Apr 2025

GLM 4.7 Thinking details →GLM 4.5 details →

FAQ

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