Tencent Hy4 burns 187M weekly tokens on OpenRouter, topping GLM 5.3 at 34M
mariofilhoml · x · 2026-09-06
Developer @mariofilhoml shared real usage numbers behind Tencent Hunyuan's Hy4 Preview topping OpenRouter's weekly ranking: last week Hy4 consumed 187M tokens ($16.20) versus GLM 5.3's 34M tokens ($10.50).
His vibe is that Hy4 on High is about 98% as good as GLM 5.3 on Max, though he wishes there were harder benchmark data. He prefers Hy4 mainly on cost: it uses fewer output tokens even on High and has a very good cache hit rate on OpenRouter. He had previously predicted Hy4 would top the weekly leaderboard after trying the model.
Related event: Tencent Hunyuan Hy4 Preview Tops OpenRouter Weekly Usage Chart(5 posts)→
More from coding & agent
- Shift-1 router cuts coding agent spend up to 55% while keeping SWE-bench accuracy — ypatil125 · 2026-10-27
- StackChan robot performs a drama skit via Hermes agent and GPT-Luna-6 — alexcovo_eth · 2026-10-27
- Prompt your agents at the grammar, noun, and verb level for saner interfaces — arvindsatya1 · 2026-10-27
- Infini-AI Lab open-sources Hermit, a framework for agent harness evolution and continual learning — BeidiChen · 2026-10-27
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- Dev ships 1000+ commits with agents by pushing straight to main, no complex orchestration — Dimillian · 2026-10-27