One API key, many AI models — with usage history and vector collections in reach
APIpie AI puts a lot of model providers behind one endpoint. Connect it with an API key and Luumen can read your model catalog with pricing and capabilities, pull query history with latency, token counts, and cost, and list the vector collections on your account. Changes — new collections, state settings, file uploads — are previewed and approved before they run.
13 tools: 8 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed APIpie AI run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create vector collection, delete state, delete vectors, update state settings, and more — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to APIpie AI — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.