Z.ai: GLM 4V Plus API

A premium flagship multimodal model optimized for simultaneous image and video understanding. It features a "Thinking Mode" for complex visual reasoning and supports high-resolution processing with native time-index tokens for video analysis, rivaling Gemini 2.0 Pro in visual agentic tasks.

Frequently Asked Questions

What is the context window of GLM 4V Plus?

GLM 4V Plus supports a context window of up to 8,192 tokens.

Does GLM 4V Plus support function calling?

Yes. GLM 4V Plus supports tool / function calling.

Does GLM 4V Plus support reasoning?

Yes. GLM 4V Plus is a reasoning-capable model.

What is the knowledge cutoff of GLM 4V Plus?

The knowledge cutoff of GLM 4V Plus is 2025-10-31.