Is DeepSeek V3.1 Terminus (Thinking) or GLM 4.5 cheaper?

DeepSeek V3.1 Terminus (Thinking) is cheaper on output tokens ($0.70 vs $1.30 per 1M).

Which has the larger context window, DeepSeek V3.1 Terminus (Thinking) or GLM 4.5?

Both models offer a similar context window.

DeepSeek V3.1 Terminus (Thinking) vs GLM 4.5

DeepSeek V3.1 Terminus (Thinking) is cheaper on output tokens. Choose DeepSeek V3.1 Terminus (Thinking) or GLM 4.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	DeepSeek V3.1 Terminus (Thinking)	GLM 4.5
Provider	NanoGPT	NanoGPT
Input / 1M tokens	$0.25	$0.30
Output / 1M tokens	$0.70	$1.30
Context window	128K	128K
Parameters	—	355B
Open weights	No	No
Released	Sep 2025	Apr 2025

DeepSeek V3.1 Terminus (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.