Skip to content
llms.party

Authentication

Every client request carries a virtual key as a bearer token:

curl -sS "https://llms.party/v1/models" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY"

Virtual keys are issued by your administrator. Each key is bounded in three ways:

BoundMeaning
Model listThe exact model groups the key may call, frozen when the key is issued.
BudgetA dollar ceiling per window, enforced by the gateway.
Budget windowThe window resets on its own; it is not a key expiry.

Grants are frozen when a key is issued

A key's model access is recorded at creation time. Adding a model group does not extend existing keys; ask for a new key. GET /v1/models is the authoritative list for a key.

Try a key from this page

The playgrounds keep the key in this tab's sessionStorage and send it only to the gateway. This panel is shared by every playground on the page.

Stored in this tab's sessionStorage and sent only to the gateway as a bearer token. It is cleared when the tab closes.

Status codes

StatusMeaning
401Missing, malformed or revoked key, or key_model_access_denied for an out-of-scope group.
403The edge blocked the path because it is not on the client allow-list.
422The key is over budget, or the request failed validation.
429The key or the upstream provider is rate limited.

The gateway checks the budget before each request; it does not reserve budget for work that is still running. Video tasks are charged when they report cost, so concurrent creates can overspend before the next call is rejected. A key stops working for every call once the budget is spent, including polling a video job. Give a key enough budget for the whole job lifecycle, not just task creation.

Rotation and revocation

Ask your administrator for a new key when one may have leaked. Revocation takes effect on the next request; there is no cache to wait out.