Z.ai launches ZCode IDE for GLM-5.2 with BYOK support

Z.ai has just rolled out ZCode, its official development environment for GLM-5.2 across macOS, Windows, and Linux. The company touts BYOK support, boosted quotas for GLM Coding Plan subscribers, and a new Max plan aimed at high-volume workloads.

•
Z.aiGLMOpen Source
z-ai cover

TL;DR

  • ZCode launched: Official development environment for GLM-5.2
  • Platform support: macOS (Apple Silicon/Intel), Windows (64-bit/ARM64), Linux beta (.deb and .AppImage)
  • Current installers: v3.2.2 listed on downloads page
  • Plans/quotas: GLM Coding Plan subscribers claim 1.5x usage quota; BYOK supported
  • Max plan pricing: $144/month (struck-through $160); includes 20x Lite usage, early features/models, dedicated peak resources
  • Settings shown: Light/English options; “Inherit system terminal profile” covers shell env, proxy, Kubernetes vars, terminal font

Z.ai on Wednesday introduced ZCode, which it described as the official development environment for GLM-5.2, alongside claims that GLM Coding Plan subscribers get "1.5x usage quota" in the app, BYOK is supported, and the software is available on macOS, Windows, and Linux.

A linked downloads page lists ZCode installers at v3.2.2 for macOS (Apple Silicon and Intel), Windows (64-bit and ARM64), and Linux in beta, with .deb and .AppImage packages. Separate pricing material for a "Max" plan places it at $144 per month, down from a struck-through $160, and describes it as being for "high-volume workloads" with "Everything in Pro, plus 20x Lite usage," "first access to the latest flagship models and features," and "dedicated resources during peak times."

Source: Z.ai on X

Continue the conversation on Slack

Did this article spark your interest? Join our community of experts and enthusiasts to dive deeper, ask questions, and share your ideas.

Join our community

Related Articles

llm cover

Coinbase says smarter AI routing cut spend nearly in half

Coinbase CEO Brian Armstrong says the company kept AI spending nearly flat as tokens rose. He credits better defaults, model routing, and cache-aware requests—not tighter caps. The approach leans more on open-weight models and leaner context.

2 shared tags
GLM-5.2 benchmark hype questioned after real-world code audit

GLM-5.2 benchmark hype questioned after real-world code audit

In a post on X, Paweł Huryn says GLM-5.2 looks “clearly worse” than GPT-5.5 and Opus 4.8 in his blind-graded bug-hunt. Across 60 audits, GPT-5.5 and Opus improved with max reasoning, while GLM-5.2 didn’t.

1 shared tag
Zai.org launches GLM-5.2 with open weights and upgrades

Zai.org launches GLM-5.2 with open weights and upgrades

Zai.org has just rolled out GLM-5.2, billed as “Frontier Intelligence, Open Weights.” The announcement points to major gains in coding and agentic tasks, with another promised strength only partially visible. A repost by Jiayuan Zhang quickly drew over 1,100 shares.

1 shared tag