MVP: docs on withohm.dev · chat edge = local :8081 (or your deploy) · api.withohm.dev returns edge-pending until AWS cutover. Status

Pricing

You pay Ohm. We pay OpenAI (and other providers) from our own balance. Those are separate ledgers.

Billing model (MVP)

Stripe invoices a monthly subscription seat. /v1/usage shows hit/miss/fetch estimates until Stripe meters ship.

EventEstimate
Cache hitCheap token hit price — served from Redis
Cache missMiss price — includes upstream fetch
Web fetchPer-fetch ingest when fetch_web_context is used

Live numbers: GET /v1/enterprise/skus and GET /v1/usage (invoice_basis: subscription_seat).

Enterprise

Monthly dedicated pool SKU: capacity features only. No published contractual uptime SLA for MVP.

Stripe

  • Admin checkout: POST /v1/admin/tenants/{id}/checkout
  • Cancel / payment failed → tenant suspended → 403
  • Return URLs: /billing/success · /billing/cancel

Design partners

Complimentary time-boxed keys (plan=design_partner) — see design partners.

Savings (estimates only)

GET /v1/usage and GET /v1/savings expose estimated upstream cost avoided from cache hits — not guaranteed savings. Ohm’s invoice and upstream provider costs are separate ledgers.