LLM API

LLM API provides a unified inference API for text, embeddings, images, audio, video, files, and batch workloads across multiple AI providers.

What agents can do

Cancel batch
Request best-effort cancellation of an in-progress batch.
Count anthropic message tokens
Count input tokens for an Anthropic-compatible message request without generating a model response.
Create anthropic message
Generate one complete, non-streaming Anthropic-compatible message with flexible content blocks, system prompts, and tool use.
Create chat completion
Generate a complete, non-streaming OpenAI-compatible chat response from role-based messages, optionally using tools, multimodal content, structured output, reasoning, or web search supported by the…
Create embeddings
Create vector embeddings for one text or a batch of texts with a selected embedding model.
Create response
Generate one complete, non-streaming OpenAI Responses-compatible result from text or structured input, preserving reasoning and tool items.
Delete file
Permanently delete a caller-owned or explicitly authorized project file.
Discover models
Return one model's full live capabilities by ID, or browse a compact, bounded view of the live model catalog using local capability filters.

4 more

Get account and credits
Return the connected user, project, organization, purchased and bonus credit balances, funding mode, and balance gating in one account-status read.
List or get batches
Return 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 or get files
Return metadata for one project file by ID, or one provider-default page of project file metadata when no file ID is supplied.
Submit batch
Create 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.

You paste an API key from LLM API on a page Composio hosts, so the key never passes through Definable.

Keep the connection to yourself or share it with your workspace. Any action that writes or sends can wait for your approval.