Perplexity Open-Sources Decider v1.3 and Decider Flash v1.3
Character-offset span extraction built into a small open-weight model removes a common glue-code step where teams wrap LLM output with fuzzy string matching, and the 6.54-point gain over Perplexity's own production classifiers suggests targeted models now beat prompted general LLMs for extraction workloads. Engineering teams handling PII redaction, entity extraction, or document classification should benchmark Decider against their current pipeline using the free OpenRouter week. Availability on Hugging Face also lets regulated industries run the weights on-premise.
Perplexity has open-sourced the latest versions of its Decision Models, Decider v1.3 and Decider Flash v1.3, releasing the weights on Hugging Face and making them free to use on OpenRouter for one week. The models are also available through Perplexity's own Decisions API under the identifiers pplx-decider-v1.3 and pplx-decider-flash-v1.3.
The headline capability in v1.3 is "locate": given a natural-language description of what to find, the model returns the matching text with exact character offsets. This makes the models suited to batch-mode decision pipelines and evidence or entity extraction, where pinpointing source spans matters. Perplexity reports that across 17 out-of-domain NER, PII, and extractive QA tasks, Decider models significantly outperform the best general extraction model, and that on 63 of the company's own production classification tasks, v1.3 is 6.54 points more accurate than the classifiers currently in production.
The release signals Perplexity positioning specialised decision and extraction models as a cheaper, more accurate alternative to running general-purpose LLMs for structured output work. Developers building document processing, compliance, or data-pipeline systems can now evaluate open weights locally or route through OpenRouter, while the free week lowers the barrier to benchmarking against incumbent extraction tools.
We're open-sourcing our latest versions of Decision Models: Decider v1.3 and Decider Flash v1.3, and making them free on @OpenRouter for a week. The new capability in v1.3 models is "locate". This lets you describe what to find, and the model returns the matching text with character offsets. This is useful for batch-mode decision + evidence/entity extraction. On 17 out-of-domain NER, PII and extractive QA tasks, Decider models significantly outperform the best general extraction model. And, on 63 of our own production classification tasks, v1.3 is 6.54 points more accurate than the classifiers we run today. Weights are open on Hugging Face: perplexity.ai/hub/blog/perpl… Perplexity Developers @perplexitydevs We're rolling out pplx-decider-v1.3 and pplx-decider-flash-v1.3, the latest version of our open-weight decision models. v1.3 adds locate, a new feature that extracts spans based on type or instructions. Now available in our Decisions API, @huggingface , and @OpenRouter . perplexity.ai/hub/blog/perpl…
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Perplexity, Decider, OpenRouter, Hugging Face.
Source attribution: curated from Aravind Srinivas (@AravSrinivas).
