Stop rebuilding the same limits for every app.
Per-user caps, plans, credits - the same boring backend, every time. Define plans in the dashboard, wrap the AI call in reserve(): quota holds atomically, no race at 1ms apart.
You know this schema. You’ve written it before.
Every AI call — quantity, cost, metadata.
→ counters · personsAtomic increments. reserve holds quota 60s.
→ plans & limitsQuotas per unit, defined in the dashboard.
Current plan + full change history.
→ plans & limits · credit_ledger · personsPre-paid credits, partial burns, rollover.
→ personsEvery event and quota joined to one profile.
if (usage < limit) leaks under parallel calls. reserve → commit → release(60s TTL) doesn’t.Every user. What they did, what it cost, where they stand.
Stop checking your users with SQL. The dashboard joins every event and quota back to one person.
One compose type per job. Define it once, it writes per user.
Fifteen jobs, one API. Every card is a full tutorial with working code.
- for your usersPersonalized paywall copy The demo above - upgrade copy grounded in each user's real usage.
- for your usersLimit-reached upsell Answer the highest-intent moment with a nudge, not an error toast.
- for your usersOnboarding next step A different first step for every user, from their first events.
- for your usersCancel-flow save offer A save offer that names exactly what this user would lose.
- for your usersTrial-end email Their trial, recapped from their own events - not a template.
- for your usersPlan recommendation Pick the right tier from real usage, not a pricing-page guess.
- for your usersWinback Re-engage dormant users with what changed since they left.
- for your usersMonthly usage recap A monthly story of what they made - the retention email.
- for your usersA/B-test the copy Prove composed copy converts - or relabel it as control.
- for your usersPersonalize without creepy Consent in the type system: opt-out is a branch, not a promise.
- for youMonday churn digest Who's drifting and why, on your desk every Monday.
- for youPre-call sales brief Everything that account did, one card before the call.
- for youFounder outreach drafts Drafts to your review queue - never auto-sent.
- for youSupport context card The user's last steps and quota state, beside the ticket.
- for youVoice of customer Themes mined from real prompts your users typed.
Pay for usage, not seats.
One bill per account, every limit pooled across your workspaces. Start free, upgrade only when you outgrow a tier.
Your first AI feature, metered in production.
- Metering operations50k/mo
- Analytics events10k/mo
- Apps1
- Workspaces1
- AI analyzerIncluded
- Prompt logsNot included
- Media uploadsNot included
- SupportCommunity
For a launched app with paying users.
- Metering operations1M/mo
- Analytics events5M/mo
- Apps5
- WorkspacesUnlimited
- AI analyzerHigher usage
- Prompt logs30-day retention
- Media uploadsIncluded
- SupportEmail
Scale across apps and millions of calls.
- Metering operations10M/mo
- Analytics events50M/mo
- AppsUnlimited
- WorkspacesUnlimited
- AI analyzerHigher usage
- Prompt logs90-day retention
- Media uploadsIncluded
- SupportPriority
Your volume and terms, on our metering rails.
- Metering operationsCustom
- Analytics eventsCustom
- AppsCustom
- WorkspacesCustom
- AI analyzerCustom
- Prompt logsCustom
- Media uploadsIncluded
- SupportDedicated
The questions devs ask first.
How do I limit OpenAI usage per user?
Define a per-user quota in the dashboard, then wrap your call in vevee.reserve(). It returns { allowed: false } the moment a user hits their cap, before you spend a cent. Any provider, any unit.
How do I stop users from bypassing rate limits with parallel requests?
A naive if (usage < limit) check has a race condition: two requests arrive in the same millisecond, both pass, both fire. Vevee exposes a reserve → commit → release pattern with a 60-second TTL so the second request sees the first reservation. Auto-released on crash or timeout.
Does Vevee process payments or proxy my AI calls?
Neither. We never touch money: keep your billing (or none) and call upsertSubscription() from your webhook. And your code calls the model directly; we sit beside the call to gate it and record it. Prompts stay yours unless you opt in.
Which AI providers does it support?
All of them. Vevee is provider-agnostic: OpenAI, Anthropic, Gemini, Mistral, Replicate, fal, or your own self-hosted model. You decide what an event is, we meter it.
What is compose() and how is it different from a prompt I write myself?
You define the compose type once in the dashboard — a prompt plus which data it can see. Vevee runs it per user, grounded in that user's real usage and behavior, returns typed output, and meters the AI cost. You never assemble the context or build the data plumbing.
The boring backend is built. Go ship the interesting part.
Five minutes from npm install to your first enforced limit. Free to 50k ops/mo, no credit card.