Skip to the content
Documentation
Help Start
Reading in:
  • German: 9,090 of 9,090 pages
About the help in other languages
All help pages

Cost control

How Exponential Intelligence keeps AI costs visible and capped - an estimated cost for every request from a price table (or the provider's reported cost), the dashboard and log, limits per conversation, session, user…

Download as PDF

Address: https://doc.exponential.earth/exphelp/viewer/help/ai-agents/governance/cost-control.md

On this page

Cost control

This page is for administrators and managers who pay for AI use. Hosted providers bill per request, by the tokens sent and received. Exponential Intelligence estimates every request's cost, shows it, and stops requests at the limits you set. A local model costs no fees, but server capacity.

Contents

  1. What a request costs
  2. Where you see it
  3. Limits
  4. Budgets for queued work
  5. Lanes and batches
  6. Habits that save money
  7. Agents outside the assistant

What a request costs

The cost of a request is, in this order: the cost the provider reported (some providers report it with every answer), the prices of its model in the settings (InputPerMTok, OutputPerMTok and the cache prices, per million tokens), or a price table by model id. A model of another provider without prices has an unknown cost rather than a guessed one; a local model is free. Prices in another currency are converted with the ECB reference rate of the day.

These are estimates from list prices. The provider's invoice is authoritative.

Every edit form shows a "Defaults in use" line with the model, region and estimated cost of a click, and the alt text note names the cost of each suggestion.

Where you see it

PlaceShowsNeeds
Dashboard > Exponential IntelligenceEstimated cost, tokens, requests and drafts with trends, a chart per day, the limitsexpai/write (own usage); expai/log for the whole site and the top users
EI: Log (expai/log)Every request with model, tokens, cost, time, tools and errors, filterableexpai/write (own), expai/log (all)
EI: Budgets (expai/budgets)The site budget, job groups, lanes, batches, held jobsexpai/log
Audit > DashboardRequests and the estimated cost of 7 daysaudit/read on the channel ai
EI: SummaryEach provider's requests, tokens and cost this month, every limit that is setexpai/summary

Limits

Set any of these in [Limits] of your expai settings; empty means no limit:

LimitResets
MaxTokensPerConversationWith "New conversation"
MaxTokensPerSessionWhen the user signs in again
MaxTokensPerUserPerDay, MaxCostPerUserPerDayAt midnight
MaxTokensPerUserPerMonth, MaxCostPerUserPerMonthOn the 1st
MaxTokensPerSitePerMonth, MaxCostPerSitePerMonthOn the 1st, all users together
MaxRequestsPerTurnThe most model calls one message may lead to
ProviderMaxTokensPerMonth[<provider>], ProviderMaxCostPerMonth[<provider>]On the 1st; only requests to that provider are stopped

A request stopped by a limit is not sent; the editor sees the limit and when it resets. While a limit is set, each request reserves its estimate before it is sent and settles with the real numbers afterwards, so parallel requests cannot overrun it together.

Budgets for queued work

Queued work (chains, translation sync, alt text reports, Vector background runs) spends money while nobody watches. Two budgets keep it in bounds (extension documentation: budgets):

BudgetSet inCounts
Monthly site budget[Budgets] SiteMonthly (else [Limits] MaxCostPerSitePerMonth)Every request of the month plus the reservations of queued requests
Job group budgetPer job group, or [Budgets] DefaultGroupBudgetThe group's settled cost plus its reservations

A queued job reserves its estimate times a safety factor. When the reservation does not fit, the job is held, with a message that names the budget and the figures, and is checked again right before its call. Held jobs resume when they fit again: through the cron part expai, ./console ext:expai:queue resume, or the button "Resume held jobs" on EI: Budgets (policy expai/settings). A new month or a raised budget frees the money.

Lanes and batches

A lane is one way of sending a request to a provider. The extension records, per provider, what it found in the provider's documentation:

LanePrice, typicallySpeed
standardList priceSeconds
flexAbout half, where offeredMinutes; may be refused when the provider is busy
batchAbout halfWithin hours (24 hours at most at the providers listed)
fastA premiumFaster; needs its own policy expai/lane_fast

The panel and the field actions always use the standard lane. Queued requests take the lane the lane policy chooses, so bulk work can go through a batch lane. The extension never uses a lane whose price it would have to guess: a lane without a confirmed price ships disabled. Plan mode in Vector shows a cost estimate before bulk work starts.

Habits that save money

  • Set a monthly site budget and a per-user daily limit from the first day; raise them when you know the real use.
  • Use a smaller model as the site default for short field actions, and allow a larger one only where it helps.
  • Use plan mode and the batch lane for bulk work.
  • Keep prompt caching on ([AISettings] PromptCaching, enabled by default): it makes repeated context cheaper.
  • Review the dashboard monthly, and the top users and models.

Agents outside the assistant

The REST API and expservices cost nothing per call themselves; the agent's own provider bills the agent's use. Limits for that live in the agent platform, not in Exponential. Let an agent page through lists with small limits (REST /limit/<n>, the limit argument of expservices lists) so it does not pull large answers into its context.

Become an Exponential Partner

Partners share their information, provide funding, contribute back and develop the products with us, and that is how Exponential grows. A partner website and dashboard are planned for mid-2027: please become a partner today to speed up our growth rate and land new features faster.

Something wrong on this page? Report an error

Documentation license

This documentation is free documentation, licensed under the GNU Free Documentation License 1.3 or later.

Exponential Copyright © 1998-2026 Exponential Foundation and 7x