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.
- Context window: 8,192 tokens
- Max output: 32,768 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2024-08-29
- Knowledge cutoff: 2025-10-31
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.