Liquid AI d1-ultra: multimodal decision model (no output tokens)
At a glance
Oct 15 ship: text+image decision model returns calibrated yes/no, choice, or score probabilities in one forward pass—no generation tokens—at $0.042/M input; pitched for defect checks, claim photos, and agent routing gates. This workflow is listed under decision-models, multimodal, agent-routing, calibration, model-release.
NVIDIA (Oct 16) details RTX Spark as a single-machine coding-agent workstation: decision models in llama.cpp/Unsloth choose next actions up to ~200x faster than long reasoning loops; HydraFusion prompt router escalates only when local models aren’t enough; GitHub Copilot gains Windows ML + llama.cpp local backend; Junie Local and Pi optimized. Pair with open Nemotron Bolt 74B-A9B 24GB for on-device agents via Ollama/vLLM/LM Studio.
Open-weight 27B decision model answers many choice/noul/score questions about one state in a single noncausal joint request (Decision Index ~68; vision ~77), with a calibrated readout head and optional fast packing path—pattern for cheap agent routing/tool selection.
Anthropic took Opus 5.5 fast mode out of research preview: set `speed: "fast"` (no beta header) for up to 2.5× OTPS at $8/$40 per MTok; separate rate limits; Claude Code `/fast` for interactive loops.