Cline made GLM-5.3 Flash (320B MoE, 18B active) completely free for all users via CLI, VS Code, and JetBrains, rapidly growing to exceed 11% of total Cline agent traffic within a single week.

Key Takeaways

  • ✓Available free directly in Cline CLI, VS Code, and JetBrains via /models -> Cline Provider -> Free;
  • ✓Features 320B total / 18B active parameters under MIT license with 1M native context window;
  • ✓Surpassed 11% of total Cline agent traffic in under a week, marking the fastest adoption in project history.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
Surpassed 11% of total Cline agent traffic in under a week, marking the fastest adoption in project history.
Full Leaderboard→
💰 Cost & PlansCompare
GLM-5.3-Flash · in: $0.15 / out: $0.5
Compare Plans↗
🛠️ Ecosystem & IDERules
Cursor · Claude Code · API
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextOpenRouter Reveals Ox Alpha as GLM-5.3-Flash: Native Multimodal Model Surpasses 20T Tokens in 6 Days
Read Now→