GLM-4

Zhipu AI · January 2024

activeCloseddecoder onlymultimodalAPI Available
Context Window130K tokens

Description

Zhipu AI's flagship multimodal model with 130K context window and strong tool-use capabilities. Built on the GLM (General Language Model) architecture lineage, it represents one of China's most capable closed-source models with competitive performance against GPT-4 on Chinese-language tasks.

Key Innovations

Multimodal
MultimodalProcessing multiple types of input (text, images, audio, video) in a single model.
Long Context
Long ContextAbility to process very long inputs (100K+ tokens), enabling analysis of entire codebases or books.
Tool Use
Tool UseAbility to call external tools, APIs, and functions — enabling web browsing, code execution, and real-world actions.

Family Tree

Successors (1)