GLM 5 Turbo

• ⚡ Latency-optimized GLM-5 variant tuned for fast agent inference.
• 🔧 Built for tool use and function-calling workflows.
• 🎯 Targets production coding and agent-driven environments.
• 📏 Context window of roughly 200K tokens.
• 🧠 Capabilities include reasoning, code optimization, and web search.
• 🏢 From Z.ai (formerly Zhipu AI), released March 2026.
• 🔒 Released under an MIT license per catalog metadata.

Z.ai

Z.ai, formally Knowledge Atlas Technology Joint Stock Co., Ltd., is a Chinese technology company specializing in artificial intelligence. Previously known internationally as Zhipu AI, the company rebranded to Z.ai in 2025. Its core focus is the GLM family of…

GLM 5 Turbo is a latency-optimized member of Z.ai's GLM-5 generation, released in March 2026 and aimed at agent-driven environments and production coding workflows. Per its catalog description, it is tuned for fast inference and strong performance in agentic settings, with listed capabilities spanning reasoning, code optimization, function-calling and web search. It carries a context window of roughly 200K tokens, suiting long documents, codebases and multi-step sessions.

Rather than a straight successor, GLM 5 Turbo is an execution-focused variant of the flagship GLM 5: where the base model targets frontier-level reasoning and coding, the Turbo version emphasizes speed and tool-calling for agent workflows. Both belong to the same GLM-5 release wave from Z.ai.

Within the same Turbo family, the later GLM 5V Turbo extends this design to native multimodal input — image, video and text. Z.ai's developer documentation describes GLM 5V Turbo as a vision-language model with tool-calling and reasoning support built on the Turbo line. Compared with Z.ai's earlier GLM 4.7 generation, GLM 5 Turbo reflects the provider's broader shift toward agent-first, low-latency serving. The catalog metadata lists an MIT license for this entry.