Liquid AI's d1-ultra decides instead of writing, charging input-only $0.042 per million tokens
JosephJacks_ · x · 2026-10-16
Liquid AI's d1-ultra is a model that doesn't generate text — it takes text and images, picks an answer, and stops. With no output tokens you pay input only: $0.042 per million. It tops Artificial Analysis' Decision Index at 65 (Jev 1.13: 58, Jev 1.14: 57), supports 44 languages, and has the best calibration error (1.5) in a 112-eval suite. Demos are deliberately boring — sorting trash from photos, picking Pokémon moves, catching broken product listings. The sharp take: half of production agent calls are yes/no or pick-one dressed up as chat completion, and someone finally priced them that way.
Related event: Liquid AI launches d1-ultra decision model, tops Decision Index(6 posts)→
More from coding & agent
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Tool calls are the hidden bottleneck killing AI coding speed — Crabbox and 5 fixes — steipete · 2026-10-16
- Agentic sandbox WorldBox doubles GPT-6 Astra's MazeBench score, 23 to 61 gems — ZhitingHu · 2026-10-16
- Two prompts: Gemini 4 Argon turns a single-player game into full multiplayer — chongdashu · 2026-10-16
- Anthropic and Gray Swan launch $300,000 indirect prompt injection red-teaming contest — bcherny · 2026-10-16