PPLX Decider v1.3
Perplexity's new model for sorting and judging questions about text and pictures, with a smaller faster version. It is made for developers building their own apps, not for everyday chat, and is private for now.
Key facts
- Released
- Nov 12, 2026
- What it does
- Not known
Can I use it?
In an app
No app mentioned so far.
For developers
No developer access mentioned so far.
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
The details
Perplexity's v1.3 decider family, a specialised classification model built on Qwen models that answers decision questions about text and images and can extract verbatim text spans. It comes in a 27B-class version needing about 49 GiB of GPU: The chip that runs AI models. Bigger models need more and larger GPUs, which is why the biggest ones live in data centres. memory and a 4B Flash version Distillation: Training a small model to imitate a bigger one, to keep much of the quality at a fraction of the cost. from it for lower Latency: How long you wait before a model starts answering. and cost; both are in a private repo.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
perplexity-ai/pplx-decider-flash-v1.3perplexity-ai/pplx-decider-v1.3Timeline
/Hugging FaceOfficialFirst signal
/Hugging FaceOfficial
Get alerts like this the moment they happen.
From Perplexity and every other major lab.