Developers

Sume developer dashboard: API keys, usage, jobs, billing, playground

Sume's developer dashboard, page by page: create API keys, buy credits on Billing & subscription, inspect Jobs and Usage, and try Avatar in the playground.

5 min readSume
All posts

The Sume docs describe five developer dashboard pages: API keys creates and manages workspace-scoped keys, Billing & subscription shows your plan and balance and lets you buy credits, Jobs lists recent API jobs with their status and errors, Usage summarizes metered activity, and the Avatar playground lets you try Avatar generation before you write code.

The details come from the dashboard section of the Sume docs: API keys, Billing and credits, Jobs, Usage, and Playground, read on 2026-09-26.

What does each dashboard page do?

The docs call the dashboard the human operator surface for the same workspace your API key resolves to. Jobs, balance, and usage can also be read over the public API. Top-ups cannot be made there: they are dashboard operations.

From the Sume dashboard docs (API keys, Billing and credits, Jobs, Usage, Playground), read 2026-09-26.
PageWhat it doesAPI endpoints the page lists
API keysCreate and manage workspace-scoped Developer API keys.—
Billing & subscriptionPlan status, available balance, and credit purchases.GET /v1/balance; no top-up endpoint.
JobsRecent Developer API jobs: status, mode, public result or error data, and timeline information where available.GET /v1/jobs and GET /v1/jobs/:id with /status, /result, /events; POST /v1/jobs/:id/cancel.
UsageA human summary of metered Developer API activity.GET /v1/usage and GET /v1/balance.
PlaygroundTry Avatar generation with your signed-in workspace context.—

How do I create and store an API key?

Create keys on the API keys page. Keys are workspace-scoped, and the dashboard reveals the full secret only when a key is created, so store it in a secure secret manager right away. Header formats, scopes, and rotation are covered in how Sume API keys work.

How do I add credits, and can I top up over the API?

Buy credits on Billing & subscription, the page older docs called "Credits". When billing is configured for the workspace, the page can start a manual credit top-up, and after checkout completes the usage ledger can show the top-up and the updated balance. The Billing and credits docs tell API clients to treat top-ups as dashboard operations, because the public API exposes balance and usage reads but no top-up endpoint.

What a generation costs is on API pricing and plans are on Pricing; how Sume pricing works explains the single wallet and on-demand purchases.

What does the Usage page show?

Usage is a human summary of metered Developer API activity. Code reads the ledger with GET /v1/usage and the balance with GET /v1/balance; both are read-only and scoped to the key's workspace. The balance is USD-denominated, and compatibility fields can show rounded cent values as credits. Depending on the workspace, ledger entries can include reservations, captures, refunds, top-ups, and grants; job ids and request ids tie rows to your generation work.

To total one thread, run, or job, add thread_id, run_id, or job_id to GET /v1/usage and quote the summary field debited_usd_micros, what the wallet deducted, instead of summing rows yourself. What one Sume API run cost walks through that summary.

Ledger statuses from Usage, read 2026-09-26.
StatusMeaning
reservedEstimated usage was reserved before provider execution.
capturedBillable usage was captured after successful completion.
refundedReserved usage was released after failure or cancellation before capture.

What are the Jobs page and the playground for?

The Jobs page is for inspecting recent Developer API jobs by hand; code reads the same jobs through the /v1/jobs endpoints in the table. Exact response shapes are in the live OpenAPI document.

The playground at /playground routes into the current Avatar playground: a human-operated way to try Avatar generation in your signed-in workspace. Use it to validate a payload before moving it into server code, CLI commands, or an agent workflow, and check exact request and response fields against the live OpenAPI schema.

Sources

Related posts

Written by Sume