Runway per-generation usage export vs the Sume GET /v1/usage ledger

For per-generation cost on Sume, call GET /v1/usage. It returns usage ledger rows for your workspace, each with a job_id and a billable_amount_usd_cents, and you can scope it with job_id, run_id or thread_id. Runway's equivalent is an enterprise-only export of credits per generation.

Sources: the Runway Dev changelog (July 28, 2026) and Sume's public API reference, read 2026-10-01.

What does Runway's export give you?

Per the changelog, organizations on an enterprise plan can export usage for web app workspaces linked to their API project. /v1/organization/webapp/usage returns one row per generation with the credits it cost, and /v1/organization/webapp/audit_logs returns audit entries filterable by actions, actorEmails and workspaceIds.

What does Sume give you?

The public API table lists GET /v1/balance and GET /v1/usage as reading the USD balance and usage ledger entries. The OpenAPI schema describes each row as scoped to the authenticated workspace, with raw provider task ids, provider URLs and idempotency keys omitted.

How do holds and refunds show up?

Paid generation reserves the estimated amount on submit and captures it on completion. Failed jobs and failed queue admission release or refund the reservation where applicable. See also balance and usage in CI.

const res = await fetch("https://api.sume.com/v1/usage?limit=20", {
  headers: { Authorization: "Bearer " + process.env.SUME_API_KEY },
});
const { data } = await res.json();
for (const row of data.usage) console.log(row.job_id, row.status, row.billable_amount_usd_cents);

Can I top up through the API?

No. The credits docs say API clients should treat top-ups as dashboard operations; the public API exposes balance and usage reads, not top-up creation.