GLM-5.3 Released for Agentic Coding at 30% Lower Cost
markjeffrey · x · 2026-08-30
GLM-5.3 and glm-5.3-flash are now live on engy.ai with verified inference. GLM-5.3 runs at 100 tps with pricing of $0.98 input, $3.08 output, and $0.18 cache per 1M tokens, which is 30% lower than OpenRouter and the official API. Additionally, Zai announced that GLM-5.3 is now open-weight, designed specifically for agentic coding and cyber defense.
More from coding & agent
- Open Source Infinite Canvas Visualizes Parallel AI Coding Agents — daniel_mac8 · 2026-08-30
- Enter Pro launches tool to build apps and agents — FellMentKE · 2026-08-30
- Enter Pro enables complex apps via natural language — FellMentKE · 2026-08-30
- Agent framework Atomic introduces Recursive State Machines — brandon_galang · 2026-08-30
- Background removal model suffers from reload overhead due to lazy loading — Acceptable-Work8202 · 2026-08-30
- Running agents in production: failures were mechanical, not the model — Wonderful-Match-6256 · 2026-08-30