GLM-4.7

AI model Released Dec 22, 2025

Context window: 204,800 tokens
Maximum output: 131,072 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

GLM-4.7

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GLM-4.7

Provider offer

GLM-4.7 / Pricing tiers 4

Provider / scope	Rate	Currency	Amount / unit
DeepInfrazai-org/GLM-4.7Standard	Cached input	USD	0.08 / 1M tokens
	Input	USD	0.4 / 1M tokens
	Output	USD	1.75 / 1M tokens
ZhipuGLM-4.7Standard 输入长度 [0, 32) 输出长度 [0, 0.2) Token tier: 0 – 32,000	Cached input	CNY	0.4 / 1M tokens
	Input	CNY	2 / 1M tokens
	Output	CNY	8 / 1M tokens
ZhipuGLM-4.7Standard 输入长度 [0, 32) 输出长度 [0.2+) Token tier: 0 – 32,000	Cached input	CNY	0.6 / 1M tokens
	Input	CNY	3 / 1M tokens
	Output	CNY	14 / 1M tokens
ZhipuGLM-4.7Standard 输入长度 [32, 200) Token tier: 32,000 – 200,000	Cached input	CNY	0.8 / 1M tokens
	Input	CNY	4 / 1M tokens
	Output	CNY	16 / 1M tokens

Capabilities

Context window: 204,800 tokens
Maximum output: 131,072 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2025-04

Input modalities

text

Output modalities

text