DeepSeek-V4.1-Flash video test: 225 min, $2.4, ~80% of Opus5.5 quality
AlchainHust · x · 2026-10-18
- The author tested the newly released DeepSeek-V4.1-Flash-1017 on video generation: a "whale travels through art history" animation took 225 minutes and cost 17.2 RMB ($2.4), which he rates at roughly 80% of Opus5.5 quality, slightly better than GPT-6 Astra.
- DeepSeek says the new model is a Pareto improvement over the previous version in benchmark performance, task completion speed, and output length, now live on web, app, and API, optimized for DeepSeek Harness, Tencent CodeBuddy, and more (Harness v0.2.1-rc.1+ recommended).
- The result relied on a proper harness and skill: the author's open-source huashu-art-motion (36 art styles, 9 narration grammars, 8 parameterized clips) animates art via code; 4.3k stars on GitHub, MIT licensed, installable via npx skills add.
More from coding & agent
- Voice booking agent on ElevenLabs + AWS: tool-turn latency hits 5s P95, how to fix? — matias_flyfishing · 2026-10-19
- Every engineering leader is building the same AI automations right now — generativist · 2026-10-19
- 'Prayer-based programming' emerges as AI coding's latest self-deprecating meme — lxfater · 2026-10-19
- Developer: I keep playing 'human API' in my AI workflows — jacalulu · 2026-10-19
- Vibe coding a parent's TV: Claude Code strips 25 Xiaomi packages, kills boot ads — HarperSCarroll · 2026-10-19
- Sentry co-founder's AI writing workflow: dictate ideas, let an agent outline, write it yourself — lmoroney · 2026-10-19