Perplexity Decider v1.2: 27B and 4B open-weight models that pick an answer and give you its probability
What is it?
These are 'decision models': give them a question and a fixed set of options, and they return one option plus a probability instead of free text. They accept text and images up to 1.6 MP and come in two sizes, the 27B pplx-decider-v1.2 on a Qwen3.8-27B backbone and the 4B pplx-decider-flash-v1.2. New in this version, every question in a request runs in a single pass, so asking several questions about the same input costs about as much as asking one.
Why does it matter?
Classification, routing, and reranking all have fixed answers, and a model like this runs those jobs at volume for far less than a chat model. Perplexity says the overall Decision Index score rose from 62.30 to 68.09Vendor claim and inference is up to 5x fasterVendor claim. The Apache-2.0 license means you can run it commercially on your own hardware.
Maturity
GAWeights are out under Apache-2.0, and both models are already on OpenRouter. The 27B model needs about 52 GiB of GPU memory in BF16.
How to track it
- Independent results: look for comparisons with other decision models like Jev on benchmarks outside the Decision Index.
- Adoption: watch the OpenRouter model pages for v1.2 pricing and where it lands in usage rankings.
- Smaller builds: check the perplexity-ai page on Hugging Face for quantized or smaller checkpoints.