Is GLM 4.6 Turbo (Thinking) or GLM 4.5 cheaper?

GLM 4.5 is cheaper on output tokens ($1.30 vs $3.00 per 1M).

Which has the larger context window, GLM 4.6 Turbo (Thinking) or GLM 4.5?

GLM 4.6 Turbo (Thinking) has the larger context window (200K tokens).

GLM 4.6 Turbo (Thinking) vs GLM 4.5

GLM 4.5 is cheaper on output tokens, while GLM 4.6 Turbo (Thinking) offers a larger context window. Choose GLM 4.6 Turbo (Thinking) or GLM 4.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GLM 4.6 Turbo (Thinking)	GLM 4.5
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$1.00	$0.30
Output / 1M tokens	$3.00	$1.30
Context window	200K	128K
Parameters	—	355B
Open weights	No	No
Released	Oct 2025	Apr 2025

GLM 4.6 Turbo (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.