Choosing a Model

A short decision guide for picking the right delivery tier.

All tiers return the same grounded, source-consistent quality. Choose on latency, cost and plan — not on accuracy.

#Pick by what matters most

If you need…UseWhy
The lowest cost per callVedika EcoEconomy path from $0.01/query; ideal at high volume.
A balanced defaultVedika StandardDeep synthesis at $0.01–$0.03; the right choice for most apps.
The newest Standard behaviourVedika Standard 2.5Set version:"2.5" on the standard path.
Sub-second, chat-grade latencyVedika Swift~1,800 tok/s, 1–3s. Business+ only.
Maximum depth, latency no objectVedika Pro UltraDeepest-synthesis profile of the standard path.

#A quick heuristic

  1. Is this a live chat/typeahead experience? → Swift (needs Business+).
  2. Is cost the hard constraint at scale? → Eco.
  3. Is this a considered reading where quality leads? → Pro Ultra.
  4. Otherwise → Standard (optionally version:"2.5").
Note
Latency figures are typical, not contractual. Per-query prices are USD; see Pricing and the live pricing page for INR and plan entitlements.

#Switching tiers is one field

Tier selection is per request, so you can route different workloads to different tiers with the same key — for example Swift for interactive chat and Eco for batch back-fills.

{ "question": "...", "birthDetails": { "...": "..." }, "speed": "fast" }