Prismatic API/Docs/Billing, quotas and PAYG
Dashboard
Documentation

Billing, quotas and PAYG

Every generation request passes through quota, PAYG and rate-limit checks before model routing starts.

Request lifecycle

  1. Authenticate the API key

    The request is attached to a customer account and API key.

  2. Resolve the public model

    The public model ID is checked against enabled catalog entries and plan access.

  3. Decide billing

    Subscription quota is reserved first. If unavailable, PAYG can reserve estimated wallet balance when enabled.

  4. Call the model route

    The request is routed only after billing and rate-limit checks pass.

  5. Settle usage

    Final usage settles quota or wallet reservations. Failed requests release reservations.

Quota and PAYG rules

  • Subscription plans use rolling 5h and 7d quota windows.
  • Each model can consume a different request multiplier per API call.
  • PAYG fallback requires wallet credit and account-level PAYG enabled.
  • Streaming PAYG requires final usage data to settle correctly.

Rate limits

  • Account-level and API-key-level limits are enforced per minute.
  • A 429 response means the request was blocked before generation.
  • Create separate keys per integration to make rate-limit diagnostics easier.
PreviousAmp