RunComfy API Docs

RunComfy provides four API products, an MCP server for AI assistants, and a CLI for the terminal. The APIs share the same high-level flow (submit > get a request_id > fetch status/results), but they solve different problems.

Serverless API (ComfyUI)

Deploy ComfyUI workflows as serverless endpoints.

Trainer API (LoRA)

Run AI Toolkit LoRA training jobs on GPUs — bring your dataset + YAML config.

Serverless API (LoRA)

Deploy LoRAs as serverless endpoints.

Model API

Run hosted models on-demand with no deployment — pay per request.

MCP

Connect AI assistants (Claude, Cursor, Windsurf) to your deployments via MCP.

CLI

Run RunComfy models from your terminal or any AI agent. One command to submit, poll, and download.

Which API should I use?

Use this as a quick decision guide:

What you are trying to do	Recommended API	What you call with	Deployment required?
Train/fine‑tune an AI Toolkit LoRA (upload dataset, run training, download artifacts)	Trainer API	`dataset_id` + `job_id`	No
Run a model from the RunComfy Models catalog (or a hosted pipeline)	Model API	`model_id`	No
Run inference with a LoRA without deploying anything	Model API	`model_id` + LoRA inputs	No
Turn a ComfyUI workflow into a production endpoint (versions, autoscaling, webhooks, instance proxy)	Serverless API (ComfyUI)	`deployment_id`	Yes
Serve a LoRA behind a dedicated, scalable endpoint	Serverless API (LoRA)	`deployment_id`	Yes

One important mental model:
Both Serverless API (LoRA) and Serverless API (ComfyUI) are built on the same serverless deployment system. The difference is what you deploy and therefore what the request schema looks like.

Getting started

Model API: start with Quickstart, then see Async Queue Endpoints.
Serverless API (ComfyUI): start with Quickstart, then learn about Overrides and workflow files.
Serverless API (LoRA): start with Choose a LoRA inference API, then follow the Quickstart.
Trainer API: start with Quickstart, then see Async Queue Endpoints (Datasets) and Async Queue Endpoints (Training Jobs).

Common request pattern

Most RunComfy endpoints are asynchronous:

Submit a job (POST …) > get an ID (request_id, job_id, etc.)
Poll status (GET …/status) until it completes
Fetch outputs (GET …/result) or use webhooks for push-based updates

If you are deploying workflows (Serverless API), you can also manage the deployment lifecycle (create/update/delete) and interact with live instances through the Instance Proxy.