H100 rental prices peaked in June; token prices keep falling while compute stays robust
AIFlow_ML · x · 2026-11-22
A chart comparing Orn's H100 GPU rental price with a token price expenditure index shows the two declining together after a June peak, then diverging: token prices fell further through August while compute prices remained robust, suggesting token deflation is driven by model efficiency rather than cheaper compute.
More from Infra
- SGLang runs Inkling 2 Mini in 65GB on DGX Spark, 2x faster prefill than vLLM — AIFlow_ML · 2026-11-22
- Open-source Agent Skill hill-climbs local LLM serving speed, users report up to 5x gains — CatAstro_Piyush · 2026-11-22
- "MoE is a datacenter architecture; looped transformers are a laptop architecture" — andreisavu · 2026-11-22
- LiquidAI's LFM3 runs on your phone; Nikita Bier's local-model thesis resurfaces — maximelabonne · 2026-11-22
- Chutes drama: TEE-encrypted inference flagged on OpenRouter despite being 'most secure' — const_reborn · 2026-11-22
- Inkling 2 Mini Beats Qwen 27B on a Single RTX 4060, Runs 3.5x Faster — LiTianleli · 2026-11-22