Case studies

Real workloads, measured.

What happens when real people use time-based AI capacity on our GPUs. Each study shows what was measured and how, grouped by who it is for.

01 — Individuals · endlesstokens

Individuals

Developers and individual consumers on a self-serve time pass.

  • A third of a billion tokens on one Daily pass

    One ₹999 Daily pass moved a third of a billion tokens, 91% from cache, on one GPU that used at most 3 of its 16 sessions. How we measured it.

    Read the case study