CometAPI
for LuumenAI
One gateway to many model providers, with quota and model checks before each call
CometAPI puts text, image, audio, and video models from several providers behind one API. Connect it with an API key and Luumen can tell you which models that key can reach, how much quota is left, and when it expires. Model calls — completions, responses, embeddings, moderation — run as previewed steps you approve.
The CometAPI toolbox
6 tools: 2 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet API Key UsageReturn quota, usage, expiration, and model restrictions for the connected CometAPI API key.
- ReadList ModelsList all models available to the connected API key, including provider ownership and supported protocol types when returned.
- WriteCreate Chat CompletionCreate a non-streaming Chat Completions result for message-based conversations and function-calling workflows. Approval by default
- WriteCreate EmbeddingsCreate OpenAI-compatible embedding vectors for one text or a batch of texts. Approval by default
- WriteCreate ResponseCreate a non-streaming OpenAI Responses API result. Approval by default
- WriteModerate ContentClassify one text or a batch of texts with an OpenAI-compatible moderation model. Approval by default
One prompt, start to finish
What a governed CometAPI run looks like inside Luumen.
Questions
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 chat completion, create embeddings, create response, moderate content — is shown as a plan and requires approval by default. 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 CometAPI — 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.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut CometAPI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.