Perplexity Decider v1.3: open decision models that return probabilities, now with Locate
Perplexity released pplx-decider-v1.3 and pplx-decider-flash-v1.3 on 12 Nov 2026: open-weight decision models (27B and 4B, Apache 2.0) that answer yes/no, multiple-choice and scoring questions with probabilities instead of text. New in v1.3 is Locate, which extracts exact text spans with character offsets.
Why it matters
Decision models that return calibrated probabilities instead of generated text - v1.3 adds verbatim span extraction (Locate), and Perplexity reports 91.6% mean accuracy across 63 classification tasks.
What you could build with it
A startup could build a compliance triage service that runs Decider over every customer support ticket and contract clause, flagging only the ones that need a human lawyer, and charge per thousand decisions instead of per seat.
Does it hold up?
Too early to judge - weights and API are live and Perplexity cites heavy internal production use, but no independent deployment writeup has appeared yet.
Built with Perplexity Decider v1.3
- Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locatemarktechpost.com · Breakdown of the release: 27B and 4B models, Apache 2.0 weights, Locate span extraction, $0.02/$0.01 per 1M input tokens.
- pplx-decider v1.3: Locate Extraction APIexplainx.ai · Spec table for v1.3: Qwen3.8-27B backbone, 262K context on OpenRouter, free window until 19 Nov.
- Perplexity Ships Decider v1.3 Classifier, 91.6% on 63 Tasksaiweekly.co · Notes the 91.6% accuracy claim carries production validation from 1B tokens across 7,000 agent sessions in a day.
Learn more
First spotted on hf: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.