thelastapi
Console
Products

Usage and limits

What the account used and what it cost, per tool, model, project, key or end user, and how close it is to today's limits.

Open as .md

Every billable unit (an AI call's tokens, an action, an email, a build, a database day) is recorded once, with what it cost to run (cost) and what the account is charged (billed).

Pricing

billed is what the account pays: our cost plus a margin (AI +10 %, actions and email +30 %, the rest +20 %; your own AI key costs 0). It is drawn from the account's prepaid credits as it is recorded (Billing). Payment fees are not usage: they come off each payment.

Limits

Every cap, its default, and how the owner changes it:

LimitDefaultChange itPast it (details.reason)
Daily spend (AI, actions, texts, calls)$5 per account per UTC dayconsole ▸ Billing ▸ Daily safety cap, or PATCH /v1/billing {"daily_spend_limit_usd": 50} (up to $1,000)429, daily_spend
Project AI budget$1 per project per UTC dayconsole ▸ project ▸ AI ▸ Daily AI budget, or PATCH /v1/projects/:id/ai {"daily_budget_usd": 10} (null: no project budget)429, project_budget
ProjectsFree plan 2, Pro 10delete one, or write to support@vibiz.ai403, project_limit
Builds30 per project per UTC dayfixed (write to support)429, daily_builds
App email50 per project per UTC dayfixed while the address builds its reputation; send newsletters as broadcasts429, email_daily_limit
Emails agents may sendnone (the owner presses Send)project ▸ Email ▸ Settings, or PATCH /v1/billing {"agent_email_limit_per_month": 5000}403, over_agent_limit
Texts / calls200 texts and 50 calls per project per UTC dayfixed429, phone_daily_limit / phone_daily_call_limit
Creditsthe account's balanceadd credits or turn on auto-recharge in Billing402 payment_required, see Billing
AI per keysee AI429 with Retry-After

Daily limits reset at midnight UTC (limits.resets_at). A refusal carries details saying which limit, the limit and usage, when it resets, raise_url (the console page that changes it, field focused) and next_step (what to tell the owner).

Limit alerts

Nobody's app should stop without its owner knowing. For every cap above:

  • At 80 % the account's owners get one email ("You've used 82% of your daily spend limit: raise it?"), and at 100 % (or when a request is refused) one more. Once per cap, project and day (month for monthly caps); a raised limit re-arms it.
  • Each email says what (which cap, which project), why (usage against the limit, what stops, when it resets) and how to fix it, with the link that opens the exact setting.
  • The console shows the same on Overview and Usage while a cap is at 80 % or more, with a Raise it button.
  • GET /v1/usage → limits.alerts lists them for agents: cap, level (warning or reached), used, limit, message, fix, raise_url.
  • An owner turns one kind of email off in Billing ▸ Limit alerts or with PATCH /v1/billing {"limit_alerts": {"daily_builds": false}}. All are on by default.

Agents building an app: tell the owner the caps it will run under and what you expect it to cost a day, set the project AI budget to fit the expected traffic, and if the app adds a cap of its own keep it under the platform's and make it tell the owner. An app must never stop silently.

Usage, cost and limits

vibiz_usage (or GET /v1/usage, vibiz usage): what was spent in a period (24h, 7d, 30d, month; group by tool, model, project, api_key, end_user, day…) and today's limits:

  • credits (prepaid accounts): balance_cents and status; at payment_required paid calls answer 402, see vibiz_billing.
  • daily_spend: spent_usd, held_usd (reserved by calls in flight), limit_usd (the account's daily safety cap, $5 by default, raisable by the owner), remaining_usd. It resets at resets_at (midnight UTC); the 24h period is a rolling window, so it can differ slightly from the calendar day.
  • projects: used / limit (10 by default). builds_today: per project, used / limit (30 a day). ai_budgets and email_today (50 a day): per project, when set or used.
  • breakdown rows: billed_usd (what you are charged), cost_usd, units (tokens, calls, …).

Payments fees are not spend: they come off the payment itself (vibiz_payments get → fees).

Check it before costly work (AI, actions, many builds) and tell the user when remaining_usd is low.

Read it

Terminal
vibiz usage                         # today, by capability
vibiz usage --period 7d --by tool
vibiz usage --by end_user --project prj_…
vibiz usage --open                  # a signed link to the hosted dashboard
Terminal
curl "https://thelastapi.dev/v1/usage?period=7d&group_by=tool" -H "Authorization: Bearer $VIBIZ_API_KEY"
JSON
{
  "object": "usage",
  "period": "7d",
  "totals": { "cost_usd": 0.42, "billed_usd": 0.42, "units": { "input_tokens": 120345 } },
  "data": [ { "tool": "ai.chat", "cost_usd": 0.31, "billed_usd": 0.31, "units": { … } } ],
  "limits": {
    "resets_at": "2026-10-26T00:00:00.000Z",
    "projects": { "used": 1, "limit": 10 },
    "daily_spend": { "spent_usd": 0, "held_usd": 0, "limit_usd": 5, "remaining_usd": 5, "used_pct": 0 },
    "builds_today": [ { "project_id": "prj_…", "used": 0, "limit": 30 } ],
    "email_today": [ { "project_id": "prj_…", "used": 0, "limit": 50 } ]
  }
}

group_by takes up to three of capability, tool, model, alias, project, api_key, end_user, day, outcome; filters project, model, tool, capability, end_user (or unattributed), api_key. model (and alias, the same) is the thelastapi model a call asked for, such as vibiz/fast; filter with model=vibiz/fast. GET /v1/projects/:id/usage is the same for one project. GET /v1/metrics has request counts, error rate and latency per capability.

End users: pass your own user's id (a stable pseudonymous id, not an email) as user on AI calls or X-Vibiz-User on anything else, or use vibiz.user(id) in @vibiz/app; usage then breaks down by end user, and end_user_daily_budget_usd caps each one's AI spend per day.

What agents can and can't do

Agents read usage (vibiz_usage) and should before costly work. Creating named keys is an owner's.