GLM-5.2

AI model Released Jun 13, 2026

Context window: 1,000,000 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-5.2

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-5.2

Provider offer

GLM-5.2 / Pricing tiers 4

Provider / scope	Rate	Currency	Amount / unit
DeepInfrazai-org/GLM-5.2Standard	Cached input	USD	0.14 / 1M tokens
	Input	USD	0.75 / 1M tokens
	Output	USD	2.4 / 1M tokens
Google Vertex AIGLM-5.2Standard	Cached input	USD	0.14 / 1M tokens
	Input	USD	1.4 / 1M tokens
	Output	USD	4.4 / 1M tokens
SiliconFlowzai-org/GLM-5.2Standard	Cached input	CNY	2 / 1M tokens
	Input	CNY	8 / 1M tokens
	Output	CNY	28 / 1M tokens
ZhipuGLM-5.2Standard	Cached input	CNY	2 / 1M tokens
	Input	CNY	8 / 1M tokens
	Output	CNY	28 / 1M tokens

Capabilities

Context window: 1,000,000 tokens
Maximum output: 131,072 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: Yes

Input modalities

text

Output modalities

text