fastH3-omni goes fully open: orchestrating open video models at ~80x less than SOTA APIs
mickeyxfriedman · x · 2026-10-21
A workflow using Claude Opus to orchestrate footage from lower-quality open-source video models costs 80x less than SOTA video APIs, with a quality comparison shown in a Squid Game demo. The math: a 15-second 1080p clip via the Seedance API with references costs $11.31, but MiniMax released H3 as open weights, and fastH3-omni — a sped-up H3 accepting reference images, video, and audio — went fully open today, maintained by the Hao AI team.
Related event: Opus Orchestrates Open-Source Video Models at 1/80 the Cost of SOTA(3 posts)→
More from coding & agent
- OvertChat: a polished self-hosted ChatGPT-style UI for local models, one-command install — anitamaxwynnn69 · 2026-10-21
- Smart Connections demo: Obsidian surfaces past decisions to reshape your plan — AINewsletter · 2026-10-21
- Ampersand v0.1 Ships via Agent API: Hosted Sessions, OpenAI-Client Compatible — gharik · 2026-10-21
- Pi Durable: Mario Zechner and Armin Ronacher on crash-safe long-running agents — mitsuhiko · 2026-10-21
- POV: Everyone's Too Busy vibe-coding Their Own Game to Play Yours — yacineMTB · 2026-10-21
- Grokbot agent drafts industrial control schematics in open-source PanelCAD — burhop · 2026-10-21