--- id: "2026-10-01-perplexity-decisions-api-pplx-decider" url: "https://postcutoff.com/e/2026-10-01-perplexity-decisions-api-pplx-decider/" as_of: "2026-11-19T22:11:00+01:00" date: "2026-10-01" date_precision: day category: model-release importance: 2 confidence: high status: [Confirmed] sources: 5 editor: human editor human_review: null version: "2026-10-10" --- As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-10-01-perplexity-decisions-api-pplx-decider/ # Perplexity launches a Decisions API and open-sources pplx-decider-v1-27b, a decision model it says edges Jev (85.71% vs 84.51%) On Oct 1, 2026, hours after Cloudflare's Clef, Perplexity released the Decisions API and the Apache-2.0 weights of pplx-decider-v1-27b, a multimodal model that returns a probability distribution over a fixed set of answers instead of text. It costs $0.04 per 1M input tokens with free output, and on Perplexity's 11-benchmark panel it scores 85.71% overall versus 84.51% for TypeSafe's Jev. It is the third Jev-style decision model in two days. ## Key facts - Model: pplx-decider-v1-27b, fine-tuned from Qwen3.8-27B; text and image input; Apache 2.0 weights on Hugging Face - API: POST https://api.perplexity.ai/v1/decisions; $0.04 per 1M input tokens, output tokens free; up to 262,144 input tokens and 1–128 questions per request - Perplexity's panel (11 benchmarks): overall 85.71% vs Jev 84.51% and base Qwen3.8-27B 74.76%; biggest gain on RAGTruth (88.80% vs 77.27%); Jev still leads on WinoGrande (90.70% vs 83.30%), BBH (94.27% vs 82.80%), JudgeBench, JevBench public hard and others - Launch post by @perplexitydevs ~242k views on X - The New Stack (Oct 9): TypeSafe's 'System One' schema is becoming the interoperability contract for decision models: AWS's open-weight Strands Decider, Upstage's Solar Decide and Ollama (from v0.35) implement the same /v1/systemone endpoint; OpenRouter, Venice and Perplexity keep the semantics on their own endpoints; OpenAI is the holdout with its own closed Decisions API (GPT-6 Luna). Three question types: choice, score and yes/no. (Article body could not be fetched; facts from the search-result summary of the article, confidence medium) ## What happened Perplexity followed TypeSafe's Jev (Sept 15), OpenAI's announced Decisions API and Cloudflare's Clef with its own decision model: a single forward pass scores every allowed option for typed questions (choice, score), so outputs are calibrated probabilities rather than generated text. The weights are open. ## Why it matters Within three weeks of Jev's launch, at least four large companies shipped compatible or competing "System One" decision models, two of them open-weight, which turns a single startup's product into a model category. All benchmark numbers are Perplexity's own. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 123 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 93 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 184 days after its cutoff - Grok 4.7 (training cutoff May 2026): 123 days after its cutoff ## Sources 1. [Perplexity docs: Decisions API quickstart](https://docs.perplexity.ai/docs/decisions/quickstart) (docs.perplexity.ai, docs) 2. [Hugging Face: perplexity-ai/pplx-decider-v1-27b](https://huggingface.co/perplexity-ai/pplx-decider-v1-27b) (huggingface.co, code) 3. [Perplexity Developers on X: Introducing the Decisions API](https://x.com/perplexitydevs/status/2105725598882832414) (x.com, official) 4. [AI Weekly: Perplexity open-sources 27B decider, edges Jev on 11-test panel](https://aiweekly.co/alerts/perplexity-open-sources-27b-decider-edges-jev-on-11-test-panel) (aiweekly.co, press) 5. [The New Stack: AWS, Upstage and Ollama agree on a decision-model API. OpenAI hasn't signed on. (Oct 9)](https://thenewstack.io/decision-models-system-one/) (thenewstack.io, press) ## Changes - 2026-10-10: Added The New Stack's Oct 9 overview of System One API convergence (body not fetchable, from search summary) - 2026-10-03 (filed): Created (AI Weekly) ## Related - 2026-10-01: [Cloudflare releases Clef and Clef-flash, open-weight multimodal decision models that are Jev-API compatible](https://postcutoff.com/e/2026-10-01-cloudflare-clef-decision-models/index.md) - 2026-09-15: [TypeSafe AI releases Jev, a 'System One' decision model that returns typed probabilities instead of text](https://postcutoff.com/e/2026-09-15-typesafe-jev-system-one-model/index.md) - Models: [pplx-decider-v1-27b](https://postcutoff.com/m/pplx-decider-v1-27b/) (`pplx-decider-v1-27b`) - Archived: 1 post, listed in https://postcutoff.com/e/2026-10-01-perplexity-decisions-api-pplx-decider/index.json