Z.ai: GLM 4.7 API
GLM-4.7 is Zhipu AI's 2026 flagship model, featuring a 355B parameter Mixture-of-Experts (MoE) architecture. Its signature innovation is the "Interleaved Thinking" system, which enables the model to reason before every response and tool call, ensuring unparalleled instruction adherence. It has gained fame as the premier engine for "Vibe Coding," capable of translating vague creative descriptions into aesthetically superior, production-ready UI/UX. Ranking top among open-weight models on SWE-bench, it rivals proprietary giants like Claude 3.5 Sonnet in autonomous software engineering and complex agentic workflows.
- Context window: 200,000 tokens
- Max output: 131,072 tokens
- Input: text, image, audio, video
- Output: text, image
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-12-20
- Knowledge cutoff: 2025-10-31
Frequently Asked Questions
What is the context window of GLM 4.7?
GLM 4.7 supports a context window of up to 200,000 tokens.
Does GLM 4.7 support function calling?
Yes. GLM 4.7 supports tool / function calling.
Does GLM 4.7 support reasoning?
Yes. GLM 4.7 is a reasoning-capable model.
What is the knowledge cutoff of GLM 4.7?
The knowledge cutoff of GLM 4.7 is 2025-10-31.