Share
GLM-5.2 from Z.ai (formerly Zhipu) landed as one of the strongest open-weight coding models of mid-2026: large MoE capacity, roughly 40B active parameters per token, and a usable 1M-token context window for long-horizon repo work. Through Orbit Provider, we’re offering GLM-5.2 at 50% off during the launch window — billed from your Orbit wallet, no separate Z.ai key required.
Coding agents thrive on models that hold a plan across many tool calls and still see enough of the repo. GLM-5.2 was built for that shape of work: multi-file refactors, long agent loops, and project-level reasoning. Independent routing markets list it well under typical US frontier API prices; our Orbit Provider promo cuts that further for Orbit users.
You can keep Anthropic, OpenAI, OpenRouter, SuperGrok, or Ollama connected at the same time and switch per chat. The promo only applies to GLM-5.2 routed through Orbit Provider.
The desktop editor remains free. Bring-your-own-key usage is unchanged and is never marked up by Orbit.
You can still reach GLM-5.2 through OpenRouter (z-ai/glm-5.2) or Z.ai’s API with your own credentials under Bring your own provider. That path uses the provider’s list prices — the 50% Orbit Provider launch rate is the managed path.
Read the Orbit Provider docs, skim the 0.4.0 release post, or jump to pricing to fund a wallet and try GLM-5.2 in Agent mode on a real repo.
Sign in with GitHub, pick a model, and start coding. Orbit 0.4.0 makes Orbit Provider first-class — with live model lists, wallet balance in the editor, and a cleaner Providers tab.
Orbit Team
Jul 20, 2026 · 4 min read
A step-by-step setup guide for connecting Ollama to your editor, picking the right model for your hardware, and knowing when a local model is the right tool for the job.
Orbit Team
Jun 5, 2026 · 5 min read
A feature-by-feature look at how Orbit Editor’s provider-agnostic approach compares to Cursor’s bundled model subscription, and which one fits your workflow.
Orbit Team
Jul 12, 2026 · 6 min read
