Vera Rubin NVL72 inference cost per million tokens vs GB200 NVL72 — one-tenth (NVIDIA ratio only; no absolute $/M-token published)
~1/10 (one-tenth)modeled
| Value kind | modeled — Interpret this value according to its displayed kind, scope, source, and as-of date. |
|---|---|
| Caveat | NVIDIA vendor ratio, not an independent measurement. CoreWeave's first-silicon result is tokens per second per megawatt (~10x), not cost; any absolute ~$/M-token appears only in secondary coverage. |
| As of | 2026-07 |
| Source | NVIDIA, Vera Rubin blog (2026-07-21) — ratio only |
| Review | checking…review by 2027-01-17 · fast cadence |
| Recorded changes | last 2026-10-19 · 2 revisions tracked |
| Claim id | vera-rubin-nvl72-inference-cost-per-million-tokens-vs-gb200 |
Where the guide uses it
Not quoted in a chapter yet; it is kept in the curated register.
← Full numbers register — every date-stamped figure in the guide, with revision history.