• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Ben Tossell Posts OpenRouter Token Throughput Data

    Ben Tossell scraped OpenRouter public pages to show live token traffic.

    RS
    BT
    3 Sources, 29d ago, first seen 29d ago

    TLDR

    Ben Tossell posted that he scraped OpenRouter's public usage pages for its top 20 apps. The post states 53.5 million tokens per second are moving through those apps at the moment of the scrape. He linked to a page on his site that presents a near-real-time view of model traffic across the same apps. The post appears as a retweet of his own account. No other sources in the packet confirm or comment on the numbers. The packet contains only the post text and the linked page title.

    Combined views

    8.9K

    3 Sources, first seen 29d ago

    Combined views

    8.9K

    3 Sources, first seen 29d ago

    13 likes
    13 likes
    5 comments
    2 saves
    7 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    5 comments
    2 saves
    7 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    3 Sources

    @ziv_ravidI don't know the details here, but I find it really hard to believe that the graph is like that because so many people suddenly started to use Codex
    @bentossellgpt model usage ⬆️since the openai + cursor breakup

    3 Sources

    @ziv_ravidI don't know the details here, but I find it really hard to believe that the graph is like that because so many people suddenly started to use Codex
    @bentossellgpt model usage ⬆️since the openai + cursor breakup