Released on Apr 7, 2026
Z.ai announced this model on 2026-04-07.
- Hosting route
- First-party API
- Affected scope
- Not stated in the notice
- Announced
- Apr 7, 2026
- First seen by ModelClock
- Oct 15, 2026
What the provider published
docs.z.ai ↗2026-04-07 GLM-5.1
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 .*
Read from the provider's text; the quote is the provider's exact lines.