pplx-decider-v1.3

by Perplexity · 27B parameters

Current new · 5d budget open weights cheap tier

Email me when pplx-decider-v1.3 gets cheaper

Availability: Sold by Perplexity through its Decisions API (POST /v1/decisions); any Perplexity API key works. Requests that name pplx-decider-latest are served by pplx-decider-v1.3 and bill at the same $0.02. Input must stay under 256K (262,144) tokens per request. The weights are on Hugging Face under Apache 2.0.

Today's price · per 1M tokens

Input

$0.020

per 1M tokens

Output

per 1M tokens

Blended

$0.015

blended $/1M — 3:1 weighted input:output

How this price is scoped: Perplexity's own pricing page lists pplx-decider-v1.3 at $0.02 per 1M input tokens, output tokens Free, per-request fee None, the same rate as v1.2. You pay for input only: the content you send, every question and any images all count as input, so a request with 600 input tokens costs $0.000012. The $0 output here is Perplexity's published rate, not a missing number. With web grounding on, each web search or URL fetch adds $0.001.

Source: official Perplexity pricing · read Nov 13, 2026 MODELPRICEWATCH.COM · 2026-11-14

Price receipt

We read Perplexity's own pricing page on Nov 13, 2026 and found pplx-decider-v1.3 listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 386835741b.

Overview

Perplexity's 27B decision model and its Decisions API default since November 2026. It reads text, JSON or images plus your questions and returns a probability for each answer (yes or no, one of your options, or a level on your rubric), not generated text. v1.3 is a new build of pplx-decider-v1.2 on the same Qwen3.8-27B base, with better accuracy and robustness per Perplexity. It adds `locate` questions, which return the spans of a text input that match a description with character offsets and a score for each. Questions in one request are now answered in one pass but kept isolated from each other. $0.02 per 1M input tokens; output is free and there is no per-request fee.

Run it yourself