Nebius hits 67B tokens/day on OpenRouter, but rivals process up to 2T daily
AccBalanced · x · 2026-10-25
After introducing cached tokens, Nebius Token Factory's volume on OpenRouter spiked to 67.1B tokens/day — impressive, but with context: Fireworks AI and Baseten typically process 200B–400B per day, and Together AI 1T–2T. Meanwhile Nebius disclosed in Nov '25 that Prosus alone ran up to 200B tokens/day on dedicated endpoints, before the Claude Code moment and open-source price drops. Raw OpenRouter numbers badly understate the competitive picture.
Related event: Nebius cached-token pricing boosts OpenRouter daily traffic to 67B tokens(2 posts)→
More from Infra
- Running big models on a single RTX 4090: INT8 weights, FP8 decoder, RAM tiering — AIFlow_ML · 2026-10-25
- ByteDance, Alibaba and Tencent order 3M+ Nvidia RTX PRO 5500 cards worth $35B+ — Miles_Brundage · 2026-10-25
- OpenRouter analysis finds evidence of spoofing-style price manipulation by inference providers — AccBalanced · 2026-10-25
- EmbeddedLLM receives AMD MI350X server donation to advance vLLM ROCm work — AccBalanced · 2026-10-25
- 106 Tesla Megapacks to replace a former Belgian coal plant with 400 MWh storage — XFreeze · 2026-10-25
- Running Qwen 3.8 Flash Next on 2x CMP 170HX mining GPUs, config shared — leonbollerup · 2026-10-25