Today we release Open d1: two open-weight multimodal models in our d1 decision model family.
> d1-3B: text + vision
> d1-omni-600M: text + image or text + audio
> Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge.
1/
d1-3B makes text and vision decisions in a single forward pass, with reported latency from 8 ms on an RTX 4090 to 50 ms on a Jetson Orin Nano. open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → and llama.cpp support allow local guardrailsThe checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.Full definition → and rerankingA second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.Full definition →.
Terms in this piece · Glossary
reranking — A second pass that re-scores retrieved candidates by reading each one against the query, fixing the ordering that fast vector search got approximately right.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
guardrails — The checks around a model that block bad inputs and outputs — filters, validators, and permission rules the model itself can't override.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
postLiquid AI's d1 decision model adds vision at a fraction of frontier cost
articled1 is now available on @vercel AI gateway!We worked with the amazing vercel…
postLiquid AI ships d1, a decision model for structured software tasks
postLiquid AI Ships Speculative Decoding for Its Vision-Language Models