Skip to main content
Models/Z.ai/GLM-5.3

GLM-5.3

Z.ai 🧠 Language Model

Z.ai's newest flagship for agentic and coding tasks. Always reasons; text-only input.

Specifications

Input modalitiestext
Output modalitiestext
Capabilitiestools, reasoning
Relative speed●●○○○ Relaxed
Context window204,800 tokens
Max output131,072 tokens
Vision inputNo
Tool callingYes
Streaming outputYes
Input price$2.45 / 1M
Output price$7.70 / 1M

Pricing

$2.45 / 1M input tokens  ·  $7.70 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use GLM-5.3 on Zubnet →

More from Z.ai

G
GLM-5
Most capable Z.ai model. 744B params (40B active MoE), 28.5T training tokens. Built for complex systems engineering and agentic tasks.
🧠 Language Model
G
GLM-5V Turbo
Native multimodal coding model. 744B MoE (40B active), 203K context. Optimized for design-to-code, GUI automation, and vision-grounded agentic tasks.
🧠 Language Model
G
GLM-4.7
Latest flagship. 358B params, 204K context, 131K output. #1 on LiveCodeBench.
🧠 Language Model
G
GLM-4.6
Flagship model with reasoning, coding, and agentic capabilities. 128K context.
🧠 Language Model