FULL STORY
Perplexity's Open-Source Decision Model Debuts, Then Tops HF Decision Index
Perplexity open-sourced its 27B multimodal decision model pplx-decider-v1 on Oct 2, and days later the v1.1 release topped Hugging Face's newly launched Decision Index, marking a clear release-to-results progression.
2026-10-02 ~ 2026-10-07 · 2 episodes · 16 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 pplx-decider-v1.1-27b, Tops HF Decision Index (2026-10-07, 8 posts)
Perplexity released pplx-decider-v1.1-27b on October 7, an open-weights multimodal decision model that ranks first on the newly launched Hugging Face Decision Index 0.3 benchmark. Weights are available for download on Hugging Face, and API input pricing has been halved versus v1 to $0.02 per million input tokens.
Confirmed
- Perplexity released the open-weights multimodal decision model pplx-decider-v1.1-27b, which scored highest on the Hugging Face Decision Index 0.3 benchmark
- Pricing is half that of v1, at $0.02 per million input tokens
- Team member antoinechaffin said the model was iterated from v1 during a weekend sprint; on Decision Index v0.2, the same backbone raised the score from 56.4 to roughly 61.5, about 3.5 points ahead of then-second-place Jev, and it went straight to the top when the v0.3 leaderboard was released
- The model is publicly downloadable on Hugging Face and usable via API at very low cost; antoinechaffin specially thanked multimodalart for building the evaluation and leaderboard, and for helping run scores when the team submitted to v0.2
Why it matters
- With the dedicated benchmark for decision models (Decision Index) just launched, Perplexity immediately topped it with an open-weights model, demonstrating rapid iteration in this niche
- Open download plus halved API pricing sharply lowers 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