{"type":"post","id":"perplexity-decider-v1-3-training-eval-and-use-816024","slug":"perplexity-decider-v1-3-training-eval-and-use-816024","title":"Perplexity Decider v1.3: Training, eval, and use cases","description":"Perplexity has released Decider v1.3 and Decider Flash v1.3, decision models for classification, scoring, routing and, newly, extracting text spans.","retrieval_nugget":"Perplexity has released Decider v1.3 and Decider Flash v1.3, decision models for classification, scoring, routing and, newly, extracting text spans. The update gives teams a structured-output component that can be tested without free-form generation, but its published performance figures are still company-reported results rather than a deployment guarantee.","published_at":"2026-11-13","updated_at":"2026-11-13","record_date":"2026-11-13","date_kind":"published_at","topics":["models"],"entities":["Perplexity","Perplexity Decider v1.3","Perplexity Decider Flash v1.3","OpenRouter","Qwen3.8-27B","Qwen3.5-4B"],"related_patterns":["model-answers-become-task-interfaces"],"novelty_label":"new_fact","what_changed":"Perplexity has released Decider v1.3 and Decider Flash v1.3, succeeding the v1.2 models and identifying Qwen3.8-27B and Qwen3.5-4B.","prior_refs":["https://newruntime.com/posts/perplexity-s-pplx-decider-v1-2-is-a-c3587d/"],"source_url":"https://www.perplexity.ai/hub/blog/perplexity-decider","source_urls":["https://www.perplexity.ai/hub/blog/perplexity-decider"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:perplexity-decider-v1-3-training-eval-and-use-816024","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/perplexity-decider-v1-3-training-eval-and-use-816024/","markdown":"https://newruntime.com/posts/perplexity-decider-v1-3-training-eval-and-use-816024.md","json":"https://newruntime.com/posts/perplexity-decider-v1-3-training-eval-and-use-816024.json"},"markdown_url":"https://newruntime.com/posts/perplexity-decider-v1-3-training-eval-and-use-816024.md","next_reads":[{"type":"topic","path":"/topics/models/","url":"https://newruntime.com/topics/models/","title":"Models","reason":"Explore the models topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/models.md","json_url":"https://newruntime.com/topics/models.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}