'%3e%3crect%20x='16'%20y='51'%20width='68'%20height='27'%20rx='13.5'/%3e%3ccircle%20cx='32'%20cy='53'%20r='15'/%3e%3ccircle%20cx='53'%20cy='43'%20r='20'/%3e%3ccircle%20cx='71'%20cy='57'%20r='12'/%3e%3c/g%3e%3c/svg%3e){kind=small}
Cloud Changelog
April 7, 2026 · Z.ai
GLM-5.1 released, working independently for up to 8 hours in a single run
- Designed for long-horizon tasks, GLM-5.1 can work independently for up to 8 hours in a single run, enabling a full loop from planning and execution to iterative refinement and final delivery.
- It demonstrates stronger engineering intelligence across autonomous planning, sustained execution, bug fixing, and strategy iteration, while achieving comprehensive capability alignment with Claude Opus 4.6. Built with multi-turn SFT, RL, and a process-quality evaluation framework, GLM-5.1 further improves stability, consistency, and tool use over extended tasks. Learn more in our documentation.*
Latest Z.ai API changes
New model adds native visual capabilities, with 320B total and 18B active parameters
GLM-5.3 released, with 50% coding gain over GLM-5.2 on Z.ai Code Bench
Model adds 1M lossless context, with stronger long-horizon task performance
GLM-5 released for complex system engineering and long-range Agent tasks
GLM-Image image generation model released, with improved text rendering