LLM API for AI agents
Agents read LLM API at once. Changes and sends are held for a person's approval by default.
About LLM API
LLM API provides a unified inference API for text, embeddings, images, audio, video, files, and batch workloads across multiple AI providers.
What an agent can do in LLM API
Every LLM API action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in LLM API without asking first. 4 actions.
- Discover ModelsReturn one model's full live capabilities by ID, or browse a compact, bounded view of the live model catalog using local capability filters.
- Get Account and CreditsReturn the connected user, project, organization, purchased and bonus credit balances, funding mode, and balance gating in one account-status read.
- List or Get BatchesReturn one asynchronous batch and its latest lifecycle, token, and cost status by ID, or one provider-default page of project batches when no batch ID is supplied. List mode supports provider cursor p
- List or Get FilesReturn metadata for one project file by ID, or one provider-default page of project file metadata when no file ID is supplied. List mode supports purpose filtering and provider cursor pagination.
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 4 actions.
- Cancel BatchRequest best-effort cancellation of an in-progress batch. Return the provider's actual batch state without implying cancellation took effect; work may still finish and incur charges before the request
- Create EmbeddingsCreate vector embeddings for one text or a batch of texts with a selected embedding model.
- Delete FilePermanently delete a caller-owned or explicitly authorized project file. This destructive operation cannot be undone; a missing file fails with not found rather than reporting a successful deletion.
- Submit BatchCreate an asynchronous batch from an existing purpose=batch file ID, or upload a JSONL input file with purpose=batch and create the batch in one call.
Changes wait in Needs you
Changes and sends in LLM API are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
LLM API questions
Can an agent change data in LLM API on its own?
Not by default. Changes and sends in LLM API are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in LLM API?
This connector lists 4 read actions. Reads run at once, without waiting for approval.
How does LLM API connect?
It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.