FULL STORY
Perplexity's Open-Source Decider: From Release to Top of the Leaderboard
Perplexity open-sourced its multimodal decision model pplx-decider-v1-27b in early October, then shipped v1.1-27b, topping Hugging Face decision benchmarks at the lowest inference cost.
2026-10-02 ~ 2026-10-10 · 3 episodes · 27 posts
Episode 1 · Perplexity Open-Sources pplx-decider-v1-27b Decision Model (2026-10-02, 8 posts)
On October 2, Perplexity CEO Arav Srinivas announced the open-source multimodal decision model pplx-decider-v1-27b, with weights uploaded to Hugging Face (perplexity-ai/pplx-decider-v1-27b) and served through the new Decisions API at $0.04 per million input tokens with free output tokens. Unlike conventional language models, it produces probability distributions over fixed answer sets instead of text, positioning itself as a decision component for software systems.
Confirmed
- The model is named pplx-decider-v1-27b, roughly 27B parameters. According to rm-rf-rm and inductionheads, it is fine-tuned from Qwen3 27B; jedisct1 relayed that it is based on Qwen3.8-27B with a 250k context window; inductionheads characterizes it as a "generative discriminator"
- It supports multimodal understanding: per victormustar and Maziyar Panahi's inspection of the Hugging Face model card and chat template, the model handles image and video inputs
- Per Perplexity researcher denisyarats, the Decisions API runs this model underneath, reading text, JSON, or images and returning structured answers with probabilities rather than generated text for direct software use
- Pricing is $0.04 per million input tokens, with output tokens free
- The announcement posts included no benchmark results or technical details
Why it matters
- A decision model compresses LLM capability into programmable probabilistic output, removing free-text parsing and fitting directly into software workflows
- The combination of open weights and a cheap API lowers the barrier for developers to try it in routing, classification, and selection tasks; victormustar sees it as another alternative in the emerging decision-model space (the Jev lineage)
- Perplexity open-sources multimodal decision model at $0.04 per million input tokens — AravSrinivas · 2026-10-02
- Perplexity quietly releases pplx-decider-v1-27b on Hugging Face — victormustar · 2026-10-02
- Perplexity open-sources pplx-decider-v1-27b, fine-tuned from Qwen 27B — jedisct1 · 2026-10-02
- Perplexity launches Decisions API: probability-based answers at $0.04/M input tokens — denisyarats · 2026-10-02
- Perplexity uploads pplx-decider-v1-27b model to Hugging Face — MaziyarPanahi · 2026-10-02
- Perplexity open-sources 27B decision model, Decisions API at 4 cents per million input tokens — hwchase17 · 2026-10-02
- Perplexity open-sources Decider 27B, a decision model fine-tuned from Qwen3 — rm-rf-rm · 2026-10-02
- Perplexity open-sources pplx-decider-v1-27b, a fast generative discriminator at $0.04/1M tokens — inductionheads · 2026-10-02
Episode 2 · Perplexity Open-Sources Decider v1.1, Tops Both Decision Index and DecisionBench at Lowest Cost (2026-10-07, 16 posts)
Perplexity released the open-weight multimodal decision model pplx-decider-v1.1-27b on Oct 7, ranking first on the newly launched Hugging Face Decision Index 0.3; on Oct 9 CEO Arav Srinivas announced it also tops the open benchmark DecisionBench at the lowest cost. Weights are downloadable on Hugging Face, API input price is halved to $0.02 per million tokens (output free), and the model is available via OpenRouter.
Confirmed
- Perplexity released pplx-decider-v1.1-27b, an open-weight multimodal decision model that scored highest on Hugging Face's Decision Index 0.3, with the API available simultaneously and listed on OpenRouter (relayed by AravSrinivas, perplexityai, gaganghotra and others)
- Pricing halved versus v1: $0.02 per million input tokens, output free
- In a clinical decision evaluation it answered 643 of 669 questions correctly, beating closed-source rival Jev's 628 at roughly 42% lower cost (announced by AravSrinivas, relayed by inductionheads and bowangbo)
- On Oct 9, AravSrinivas announced Decider V1.1 ranked first on DecisionBench at the lowest cost: 93.9% accuracy and 534ms latency. DecisionBench is an open benchmark for small-model "bounded decisions" built from real records, covering engineering, agents, customer support, finance, legal and more, with reproducible accuracy/latency/cost metrics
- Unlike typical generative models, it does not generate text: it reads text/JSON/image inputs and returns a typed decision with probabilities in a single request, suited for classification/routing tasks
- Team member antoinechaffin said the model was iterated from v1 over a weekend sprint; the same backbone lifted the score from 56.4 to about 61.5 on Decision Index v0.2, about 3.5 points above then-leader Jev, before topping the v0.3 leaderboard
- The model is publicly downloadable on Hugging Face and usable via a very low-cost API; antoinechaffin thanked multimodalart for building the evaluation and leaderboard and for running scores when the team submitted v0.2
Why it matters
- Dedicated benchmarks for decision models are just emerging (Decision Index and DecisionBench), and Perplexity has simultaneously topped both with an open-weight model at the lowest cost, showing rapid iteration in this niche
- Open weights, halved API pricing and multi-channel access via OpenRouter sharply lower the barrier to high-performance decision models, directly appealing to developers and cost-sensitive use cases
- Perplexity's open-weights pplx-decider-v1.1-27b tops Hugging Face Decision Index 0.3 — AravSrinivas · 2026-10-07
- Perplexity ships open-weights pplx-decider-v1.1-27b at half the cost of v1 — perplexity_ai · 2026-10-07
- Perplexity's open decider model tops new Decision Index v0.3 leaderboard — antoine_chaffin · 2026-10-07
- New model goes public on HF with cheap API, thanks to community eval leaderboard — antoine_chaffin · 2026-10-07
- Perplexity open-sources pplx-decider-v1.1-27b, tops new Decision Index at half the price — antoine_chaffin · 2026-10-07
- Perplexity's open-weights pplx-decider-v1.1-27b tops HF Decision Index at half the price — henrymodis · 2026-10-07
- Perplexity's open-weights pplx-decider-v1.1-27b tops HF Decision Index at half the price — antoine_chaffin · 2026-10-07
- Perplexity open-sources pplx-decider-v1.1-27b, tops HF Decision Index at half the cost — bo_wangbo · 2026-10-07
- Perplexity releases open-weights pplx-decider-v1.1-27b, priced at $0.02/M input tokens — inductionheads · 2026-10-07
- Perplexity ships open-weights pplx-decider-v1.1-27b, tops Decision Index 0.3 at half the cost — cameronstow · 2026-10-07
- Perplexity ships open-weights Decider v1.1: top Decision Index score, half the price — gaganghotra_ · 2026-10-08
- Perplexity's open-weights Decider v1.1 27B model lands on OpenRouter, free output at $0.02/M input — AravSrinivas · 2026-10-08
- Perplexity's open-weights Decider v1.1 lands on OpenRouter with free output at $0.02/M input — inductionheads · 2026-10-08
- Perplexity open-sources pplx-decider v1.1, beating Jev on clinical decisions at 42% less cost — bo_wangbo · 2026-10-08
- Perplexity's open-weights pplx-decider beats Jev on clinical decisions at 42% lower cost — inductionheads · 2026-10-08
- Perplexity Decider tops DecisionBench with 93.9% accuracy, 534ms latency, and lowest cost — AravSrinivas · 2026-10-09
Episode 3 · Perplexity's 27B decision model tops DecisionBench at lowest cost (2026-10-09, 3 posts)
Perplexity released pplx-decider-v1.1-27b, a Qwen-based decision model that tops the DecisionBench leaderboard with 94.5% accuracy at the lowest cost, about $0.017 per thousand decisions.
- Perplexity Decider tops DecisionBench as the lowest-cost decision model — victormustar · 2026-10-09
- Perplexity's pplx-decider-v1.1-27b tops Decision Bench with 94.5% accuracy at $0.017 per 1,000 decisions — gaganghotra_ · 2026-10-10
- Perplexity uploads mystery model pplx-decider-v1.1-27b, a Qwen3.8-27B fine-tune — perplexity-ai · 2026-10-10