Modal launches free Z.ai GLM-5 endpoint and provides self-deployment code
Original title:Try GLM-5.1, the new frontier of open intelligence, on Modal
AI summary
Z.ai released the open-weight model GLM-5 (MIT license, aimed at long-horizon agents and systems engineering), and Modal partnered with it to launch a free trial endpoint available until the end of April, limited to a single concurrent request. At FP8 precision the model is about 700 GB and requires multi-GPU deployment; Modal runs it with SGLang on a single node with 8 B200 GPUs, with internal testing showing 30-75 tokens/s per user.
Key Takeaways
- ai released the open-weight model GLM-5 (MIT license,aimed at long-horizon agents and systems…
- At FP8 precision the model is about 700 GB and requires multi-GPU deployment
- Modal runs it with SGLang on a single node with 8 B200 GPUs,with internal testing showing 30-75…
Quick Facts
- Published
- Updated
- Source
- Modal 官方工程博客(RSS)
- Category
- Products & Apps
- AI score
- 71
Modal 官方给出 GLM-5 的部署细节、免费端点限制和前端接入配置,读者可直接照做在自己常用的 Agent 框架里试用。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Modal launches free Z.ai GLM-5 endpoint and provides self-deployment code. February 11, 2026. https://new.nat6.net/en/news/cmtyo0dnt035vrog0ht75ayad/