# Perplexity: pplx-decider

> Perplexity's open decision model: Qwen3.8-27B fine-tuned with a 255-option decision readout in place of the text head. Reads text, JSON and images and returns probabilities for yes/no, choice and rubric-score questions. Also served as Perplexity's hosted Decisions API.

- Page: https://systemonemodels.ai/perplexity/pplx-decider
- API: https://api.systemonemodels.ai/v1/models/perplexity/pplx-decider
- Download: `pip install systemonemodels && systemone pull perplexity/pplx-decider`

## Facts

| | |
|---|---|
| Maker | Perplexity (https://systemonemodels.ai/perplexity) |
| Decides | choice, score, noul |
| Architecture | pplx-decider |
| Base model | qwen/qwen3.8-27b |
| Parameters | 26B |
| Context | 256K tokens |
| Licence | apache-2.0 |
| Availability | Open weights + hosted API |
| Released | 2026-10-01 |
| Latest version | 1.0.0 |

## Hosted API

- Provider: Perplexity (https://docs.perplexity.ai/docs/decisions/quickstart)
- Docs: https://docs.perplexity.ai/api-reference/decisions-post
- Input: $0.040/MTok · Output: Free

## Reported evaluation

Suite: Perplexity's 11-benchmark panel (WinoGrande, FinancialPhraseBank, RAGTruth, JudgeBench, BBH, JevBench public hard, TabFact, ContractNLI, Circa, Belebele, TruthfulQA binary), through the Perplexity API. Numbers are the publisher's own.

- Decision accuracy: 85.7%

## Model card

<!-- generated by scripts/seed_catalog.py; edit content/models/catalog.yaml -->

# pplx-decider-v1-27b

Perplexity's open decision model: Qwen3.8-27B fine-tuned with a 255-option decision readout in place of the text head. Reads text, JSON and images and returns probabilities for yes/no, choice and rubric-score questions. Also served as Perplexity's hosted Decisions API.

The readout has a temperature fitted on a separate calibration split, but no calibration error is published. The hosted API (POST /v1/decisions) takes 1 to 128 questions per request, up to 255 options per choice and 1 to 10 score levels, under 262,144 input tokens, in Perplexity's own request format (not a Jev endpoint). There is no lm_head, so the repo's inference code is needed. Perplexity reports 85.71% over its 11-benchmark panel against 84.51% for Jev, measured through its API. v1.1 (2026-10-05, perplexity-ai/pplx-decider-v1.1-27b) runs the full-attention layers noncausally and adds tasksource data; its card cites the third-party Decision Index board at 61.56 against 56.4 for v1. Weights Apache-2.0 with a NOTICE (derived from Qwen3.8-27B); the code under source/ is MIT.

## What it decides

- **choice** — picks one option from a set
- **score** — places the input on an ordered scale
- **noul** — answers a yes/no question with one probability

## At a glance

| | |
|---|---|
| Parameters | 26.1B |
| Base model | `qwen/qwen3.8-27b` |
| Maker | Perplexity |
| Released | 2026-10-01 |
| License | apache-2.0 |
| Reported accuracy | 85.7% |
| Reported latency | under 2 s for a few hundred input tokens, 5 s at about 90k, 23 s near the 262,144-token limit (Perplexity's tests, 30 Sep 2026) |

## Hosted API

Served by **Perplexity** — $0.04/MTok input, $0/MTok output. [Get access](https://docs.perplexity.ai/docs/decisions/quickstart) · [API docs](https://docs.perplexity.ai/api-reference/decisions-post).

## Get the weights

```bash
pip install systemonemodels
systemone pull perplexity/pplx-decider
```

The files are served from the maker's Hugging Face repository, [`perplexity-ai/pplx-decider-v1-27b`](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b), and verified against the checksums recorded here.

## Read more

- [Model card (v1)](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b)
- [Model card (v1.1)](https://huggingface.co/perplexity-ai/pplx-decider-v1.1-27b)
- [Decisions API quickstart](https://docs.perplexity.ai/docs/decisions/quickstart)
- [API reference](https://docs.perplexity.ai/api-reference/decisions-post)

---

*This page was opened by System One for Perplexity, who can claim the organisation and take it over at any time.*

---

From System One Models — https://systemonemodels.ai/ · every System One model: https://systemonemodels.ai/system-one-models