This post shares cost and speed data for Jev and other models on clinical decision tasks, comparing total cost across 9 APIs and noting the fastest 3GB local model responds in 284 ms.
you asked for cost and speed, so here they are 👇 pplx-decider and Jev each ran all 669 clinical decisions for about 3 cents. all 9 APIs together: 74 cents. the fastest 3 GB local model answers in 284 ms, quicker than any API i measured.
During live clinical consultations, an ambient scribe periodically feeds transcripts to Jev, which traverses a medical ontology to classify symptoms, update the differential diagnosis, suggest treatments, and flag red flags in real time.
The author demonstrates how to triage a patient to the right doctor using only TypeSafe AI's Jev model and some question-asking code, noting that no LLM is used during the conversation.
A developer shares building a calorie tracking app with Jev, highlighting its instant experience.
