Usage

See your usage and limits for LLM credits, disk space, and Agent Cloud nodes.

Three allowances bound a tenant: credits for model tokens on the platform-default model, a disk quota for provisioned storage, and a node quota for managed Agent Cloud capacity. All three are live figures under Manage → Usage, and the credits meter is mirrored in the sidebar.

The Usage page

Plan usage shows three cards: Credits, Storage, and Cloud Nodes. Separate usage sections provide more detail.

Credits

A credit is a token bucket: 1 credit per 1,000,000 input tokens and 5 credits per 1,000,000 output tokens on hosted models. New tenants are seeded with a starting allowance. Credits are consumed by platform features that call an LLM for you, like generating a policy or a skill, and by agents running on the hosted Industric Provider.

Your own provider keys do not spend credits

Agents pointed at a provider you configured bill to that provider, not to credits. Credits cover the batteries-included path, so a new tenant can run an agent before wiring up any vendor account.

At zero credits, features that need the platform LLM stop and report out_of_credits rather than failing obscurely. Buy Tokens and Buy Compute on the Usage page top up the allowance through a hosted checkout; the balance updates as soon as the payment completes.

Disk & node quotas

Quota	Counts	Enforced when
Disk (Gi)	Provisioned file systems and app storage across the tenant.	Creating or growing a volume.
Nodes	Nodes running managed Agent Cloud deployments.	Creating or resizing an Agent Cloud deployment.

A request that would cross a quota is refused with the limit that was hit — and Agent Cloud sizing reports every violation at once, not just the first, so you can correct the whole form in one pass.

Raising an allowance

Entitlements are set per tenant. Viewing them needs usage:read; purchases and allowance updates need usage:purchase. Values are absolute, not deltas — adding 100 credits means writing the current total plus 100.

limits API· http

1GET /api/v1/dashboard/limits
2PUT /api/v1/dashboard/limits    { "credits": 250, "disk_limit_gi": 500, "node_limit": 10 }

Per-agent spend

Credits and quotas are tenant-wide. For attribution — which agent, which person, which day, and what it cost in dollars — route traffic through an LLM gateway. Its usage view slices spend, requests, and tokens by agent and by user, and its budget rules cap them before the tenant allowance ever comes into play.