Sample data. These figures are not a customer bill.Learn more
parezenparezen
Northwind AI
Scale · Sample · cloud
Home
  • Get startedSoon
  • Audits
  • Overview
Analyse
  • Spend
  • Cost per task
  • Agents
  • Model comparisonSoon
  • Budgets
  • AlertsSoon
  • Reports
  • PR cost checksSoon
  • AdvisorsSoon
  • Spend analysis
Optimise
  • RecommendationsSoon
  • Routing policiesSoon
  • Shadow testsSoon
  • CachingSoon
  • TrimmingSoon
  • BatchSoon
  • Waste detectorSoon
Gateway
  • SetupSoon
  • ProvidersSoon
  • ModelsSoon
  • API keysSoon
  • DeploymentsSoon
  • PlaygroundSoon
  • LogsSoon
Savings & billing
  • Savings history
  • Savings ledger
  • Bill match
  • Billing
  • Invoices
Settings
  • Data & privacySoon
  • OrganisationSoon
  • ProjectsSoon
  • TeamSoon
  • RolesSoon
  • SSOSoon
  • Audit logSoon
Plan: Scale · Sample ↗
DocsHelp

Sample data. Not a customer bill.

Northwind AI/Caching

Caching

Planned

Provider cache hit rate and exact-match cache per route.

Hit rate
25.0%
12 of 48 sample requests
Cached input tokens
1,440
Tokens the provider priced as cached
Routes to reorder
3
Stable prefix is not in front yet

Prompt reorder

No behaviour change. Move the stable system prompt ahead of the user turn so the provider can discount it.

Support reply

Move the stable system prompt ahead of the user turn so the provider can cache it.

10,837 input tokens
Open cache policy
Document extract

Move the stable system prompt ahead of the user turn so the provider can cache it.

9,357 input tokens
Open cache policy
Eval backfill

Move the stable system prompt ahead of the user turn so the provider can cache it.

9,994 input tokens
Open cache policy