Perplexity's Decider API classifies 203,883 Phoenix aerial tiles at 98.8% accuracy for $9.63
inductionheads · x · 2026-10-13
AskPerplexity demonstrated city-scale land-use classification: using Perplexity's Decider API, it analyzed 203,883 tiles of public USDA aerial imagery of Phoenix, achieving 98.8% accuracy against labeled OpenStreetMap data at a total API cost of just $9.63 — a striking showcase of how cheap large-scale geospatial analysis has become with LLM APIs.
More from Apps
- Google lets you launch vibe-coded apps directly through the Play Store — The Verge AI · 2026-10-14
- Three agent skills for tender research: source search, bid qualification, evidence-based drafting — S3mz · 2026-10-14
- An interactive AI pet built with three.js and MediaPipe — sophiamyang · 2026-10-14
- Dev builds voice-first macOS focus assistant that nags you like your mom, powered by Sarvam's bulbul v4 — itsOmSarraf_ · 2026-10-14
- Plane Agents ship: AI agents as workspace members you assign and @ in comments — JosephJacks_ · 2026-10-14
- 20 free prompts to unlock the other 90% of Claude Cowork's SEO potential — JaynitMakwana · 2026-10-14