VQV Signal
According to a post on X by @realpython, Perplexity's Decider v1.3 and the smaller Decider Flash v1.3 ship with Apache-licensed weights on Hugging Face. Perplexity says Decider averages 91.6% accuracy across 63 query-classification tasks, at $26.47 per million requests. The accuracy and cost figures are Perplexity's own claims as relayed in the post.
According to a post on X by @realpython, Perplexity's Decider v1.3 and the smaller Decider Flash v1.3 ship with Apache-licensed weights on Hugging Face. Perplexity says Decider averages 91.6% accuracy across 63 query-classification tasks, at $26.47 per million requests. The accuracy and cost figures are Perplexity's own claims as relayed in the post.
AI-assisted summary based on the listed source.
Real Python reported that Perplexity's Decider v1.3 and the smaller Decider Flash v1.3 ship Apache-licensed weights on Hugging Face. Perplexity says Decider averages 91.6% accuracy across 63 query-classification tasks at $26.47 per million requests. Why it matters: Developers can route or classify queries with an...
Developers who pay for an API to route or classify queries could test an open model instead, since the weights are available to download. Teams should check the license terms and compare the claimed accuracy and per-request cost against their own workloads before switching. Independent benchmarks of these claims would be the next thing to watch.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to AI Search, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
