AI Wiki · Mediocre Security
CompanyModels & inference infrastructure

Perplexity

Decisions API runs pplx-decider-v1-27b, an open multimodal model that returns probabilities instead of text, at $0.04 per million input tokens with free output.

Decisions API (Oct 1 2026) runs pplx-decider-v1-27b, an open multimodal model that returns probabilities (yes/no, pick one option, rubric level) instead of text, at $0.04 per million input tokens with free output (Perplexity docs; AI Weekly). Part of a “decision model” wave with OpenAI’s Decisions API, Cloudflare Clef and TypeSafe’s Jev: fast classifiers that can gate what an agent is allowed to do. Embeddings: pplx-embed-v2-late, two late-interaction embedding models released under the MIT license (0.6B edge and 9B variants sharing one embedding space; on Hugging Face since Oct 7 2026); Perplexity reports 92.4% on MADQA (vendor claim). Retrieval layer for agents (Perplexity, via AI Weekly, Oct 9 2026). Perplexity’s SPACE agent sandbox is listed under Evaluation, monitoring & containment.

Timeline

Every dated event in the wiki that involves Perplexity, newest first.

  • Research
    Study: ChatGPT, Gemini and Perplexity point shoppers to risky retail sites

    Brand-protection firm Podqi asked the three chatbots shopping questions about 151 brands across 6,795 answers in September and found fake, re-registered or dead store domains in 15% of Perplexity answers, 8% of ChatGPT answers and 4% of Gemini answers (counting mentions that warned about the site). Podqi wrote its own prompts, and one of the brands is its client; results are one firm's test, shared with The Verge.

Connections

Perplexity and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Person Aravind Srinivas

Product ChatGPT · Perplexity SPACE

Concept Decision model · Embedding · Retrieval-augmented generation (RAG)

Company TypeSafe (Jev)

Cited by

Cited as a source by 1 timeline events.

1 articles cite Perplexity as a source: Perplexity SPACE

Sources

  1. Perplexity docs [link needed]
  2. AI Weekly [link needed]
  3. Perplexity (via AI Weekly) [link needed]