ai& runs MiniMax H3 across NVIDIA, AMD and Tenstorrent, undercutting official pricing
DavidBennett__ · x · 2026-10-22
ai& (@aiand) deployed MiniMax H3 video generation across heterogeneous NVIDIA, AMD and Tenstorrent hardware, picking the right architecture per workload and engineering around it. H3 fast starts at just $0.0125 per generated second at 768p, with the quality endpoint at $0.055, versus MiniMax's official $0.08. The team argues heterogeneous inference becomes a technical imperative, not just an optimization, as AI expands across modalities.
More from Infra
- Video Model API Markups Exposed: Runway Charges 414%, New Sume API Launches With 0% Markup — Scobleizer · 2026-10-23
- Google Cloud launches Agent Compute Engine, a new VM type built for AI agents — testingcatalog · 2026-10-23
- LM Studio ships Read Aloud, powered by tiny local TTS model Phonon from Gradium — mattturck · 2026-10-23
- Lam Research system revenue up 35% QoQ as AI pushes 2027 WFE past $200B — BenBajarin · 2026-10-23
- Hugging Face Hub launches OpenUSD support with 2,500+ NVIDIA SimReady assets — mishig25 · 2026-10-23
- One lying fsync() on a single node can make a Raft cluster lose data — tianyin_xu · 2026-10-23