Prompt Caching

Caching is automatic — no parameter to set. Here is exactly what it costs on each tier.

#How it works

Prompt and response caching is fully automatic. There is no cache-control parameter to set — repeated and short queries are served efficiently by default, with nothing to configure on your side.

#Seeing cache hits

Every response surfaces cache activity in metadata.usage.cached_tokens, so you can see, per call, how much of the request was served from cache.

{
  "answer": "...",
  "metadata": {
    "usage": {
      "input_tokens": 12084,
      "output_tokens": 291,
      "total_tokens": 12375,
      "cached_tokens": 11820
    }
  }
}
Tip
Keep context stable to maximise cache hits — reuse the same birthDetails and a stable conversationId across follow-up turns instead of re-sending fresh values each time.

#Cost impact

Caching changes your bill in two distinct ways. Which one applies depends on whether the whole answer was reused, or only part of the input was.

#1. Answer-cache hit — flat $0.01, every tier

When you repeat an identical question for the same chart, the answer is served from the Vedika answer cache without calling the reasoning engine at all. That call bills a flat $0.01 on every tier, and the usage block reports zeros because no tokens were generated:

{
  "metadata": {
    "cost": { "costUsd": 0.01, "currency": "USD" },
    "usage": { "input_tokens": 0, "output_tokens": 0,
                "cached_tokens": 0, "total_tokens": 0 }
  }
}

#2. Reused input inside a live answer

When the engine does run but part of your input is reused, those cached input tokens are priced per tier. Vedika passes through the economics of the delivery path each tier runs on: some paths bill reused input at a genuinely lower rate, and some bill it at the normal rate and return the benefit purely as speed.

TierCached input tokensWhat caching buys you
Vedika EcoReduced rate — 10% of the fresh-input rate; cache writes at 1.25 times the input rate, held 30 minutesLower read cost
Vedika Standard (default; it also answers the retired version:"2" pin)Reduced rate — 10% of the fresh-input rate; cache writes at 1.25 times the input rate, held 5 minutesLower read cost
Vedika SwiftSame rate as fresh inputLatency only — already the fastest tier
Vedika Pro UltraReduced rate — 10% of the fresh-input rate; cache writes at 1.25 times the input rate, held 5 minutesLower read cost and lower latency
Note
Cache pricing depends on the tier. Where a tier discounts cached input, you get a lower per-token rate; on other tiers, caching improves latency at the same input rate. On Vedika Eco, Standard and Pro Ultra, cache writes cost 1.25 times the fresh-input rate; an Eco write is held for 30 minutes and a Standard or Pro Ultra write for 5 minutes. Final deductions include all billable components and round to whole cents, with a $0.01 minimum for a billable answer, so a token discount may not change the final deduction. See your response billing metadata for the price and wallet deduction.

#Vedika Eco token rates

Vedika Eco is also billed per token. Rates are USD per 1M tokens: fresh input, reused (cached) input, a cache write (held 30 minutes), and output. The per-query range stays from $0.01, the minimum charge for a billable answer.

Prompt sizeInput / 1MCached input / 1MCache write (30 min) / 1MOutput / 1M
Up to 272,000 prompt tokens$0.40$0.04$0.50$2.00
Prompts over 272,000 tokens$0.80$0.08$1.00$3.00

See Pricing for the per-call rates and the rates per 1M tokens, and Model Catalog for the per-tier capability grid.