Z.ai: GLM 4 API
Zhipu AI's 4th-gen flagship MoE model (355B total/32B active). It features a "Thinking Mode" for complex reasoning, 200k context window, and native agentic capabilities. Released as an open-source rival to Claude 4 and GPT-5, it excels in bilingual coding and multi-step tool orchestration.
- Context window: 200,000 tokens
- Max output: 128,000 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2024-01-15
- Knowledge cutoff: 2025-10-31
Frequently Asked Questions
What is the context window of GLM 4?
GLM 4 supports a context window of up to 200,000 tokens.
Does GLM 4 support function calling?
Yes. GLM 4 supports tool / function calling.
Does GLM 4 support reasoning?
Yes. GLM 4 is a reasoning-capable model.
What is the knowledge cutoff of GLM 4?
The knowledge cutoff of GLM 4 is 2025-10-31.