a16z: OpenRouter token demand up ~27x in a year, open-weight models now serve 72%
TheZachMueller · x · 2026-10-26
a16z's Charts of the Week explains what's driving GPU rental prices:
- Token demand surge: Weekly tokens on OpenRouter grew 27x since last November, from 6T/week to 165T/week.
- Open-weight rise: Open-weight models now handle 72% of those tokens, up from 28% — though their share of spend remains only 25%.
- GPUs renting ahead of depreciation: Rental price premium over a standard 6-year schedule: H200 +143%, B200 +111%, RTX PRO 6000 +73%, H100 +54%, A100 +9%. Most of the gap opened after April when token demand took off.
Takeaway: inference demand is the direct driver of the tight GPU rental market, with open models absorbing most of the volume. The piece also notes Netflix's growth slowing to 12% and US weekly media consumption plateauing at 26 hours.
More from Infra
- Meta unveils $95B equity raise for AI infrastructure, stock up 2% pre-market — firstadopter · 2026-10-26
- Killed our Vector DB for SQLite BM25 and wrote a 3.6ns Rust sentinel: lessons from multi-agent loops — OpenComplaint524 · 2026-10-26
- Gemma 4 26B-A4B runs offline on a 16 GB Mac: 33/40 on TypeScript tasks at 31 tok/s — Mission-Sir-1614 · 2026-10-26
- How thousands of GPUs train one AI: a breakdown of 5D parallelism — jbhuang0604 · 2026-10-26
- Stratechery: endgame for the open web, and a coming AI startup credit crunch — tushaarmehtaa · 2026-10-26
- Running full DeepSeek V4.1 Flash weights on 4x DGX Spark (~$28k): 1M context at 66 tok/s — ricklamers · 2026-10-26