Deck
Deck

I Work in LLM API So You Don't Have To Switch Tabs

LLM API provides a unified inference API for text, embeddings, images, audio, video, files, and batch workloads across multiple AI providers. Connect it, and I work in LLM API for you when you ask.

Actions
Category
Artificial Intelligence
Actions available
12
Feedback import
Not yet
Connection
Team or personal

What I Can Do in LLM API

12 actions. Reads run right away. Changes wait for your approval.

Reads

  • Count Anthropic Message TokensCount input tokens for an Anthropic-compatible message request without generating a model response.
  • 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.
Show all 5 LLM API reads
  • 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.

Changes, with your approval

  • Cancel BatchRequest best-effort cancellation of an in-progress batch.
  • Create Anthropic MessageGenerate one complete, non-streaming Anthropic-compatible message with flexible content blocks, system prompts, and tool use with your own connection.
  • Create Chat CompletionGenerate a complete, non-streaming OpenAI-compatible chat response.
  • Create EmbeddingsCreate vector embeddings for one text or a batch of texts with a selected embedding model.
Show all 7 LLM API changes
  • Create ResponseGenerate one complete, non-streaming OpenAI Responses-compatible result from text or structured input, preserving reasoning and tool items.
  • Delete FilePermanently delete a caller-owned or explicitly authorized project file.
  • Submit BatchCreate an asynchronous batch for chat completions or responses from an existing purpose=batch file ID, or upload a JSONL input file and create the batch.

Questions About LLM API and Deck

Open Settings, then Integrations and Plugins, find LLM API and sign in. An admin can connect it for the whole team.

No. In chat, every change waits for your approval.

A team connection works for everyone in the workspace. A personal connection works only for the person who made it.

Not yet. Today I look things up and act in LLM API when you ask. Apps marked Feedback source import on a schedule.

Ready To Connect LLM API?

5-minute setup. Insights from day one.