ComfyUI API No Deployment. Just POST.

Run your workflows in the cloud with zero setup. Same JSON format you already use.

Terminal

# workflow.json - exported from ComfyUI
{
  "6": { "class_type": "CLIPTextEncode",
         "inputs": { "text": "a bottle with a rainbow galaxy..." } },
  "30": { "class_type": "CheckpointLoaderSimple", "inputs": {
         "ckpt_name": "https://huggingface.co/.../flux1-schnell-fp8.safetensors" } },
  "31": { "class_type": "KSampler", "inputs": { "steps": 4, ... } }
}

# POST to API
curl -X POST https://api.cmfy.cloud/v1/prompt \
  -H "Authorization: Bearer $API_KEY" \
  -d @workflow.json

# Response
{ "job_id": "job_abc123", "status": "queued" }

Deploying ComfyUI to production is a nightmare

You've built amazing workflows locally. Getting them to production? That's where the pain begins.

Docker containers to manage

Spinning up GPU instances, managing dependencies, handling crashes

Endpoints to configure

Load balancers, API gateways, authentication, rate limiting

SDKs to learn

New client libraries, different request formats, result handling

Cold starts eating your budget

Paying for model loading time that adds nothing to your output

The Solution

One endpoint. Your existing workflow JSON. That's it.

No deployment, no SDKs, no configuration. Just POST your workflow and get results.

Without ComfyUI API

Provision GPU server
Install CUDA, PyTorch, ComfyUI
Configure API wrapper
Set up load balancer
Handle scaling, monitoring, uptime
Debug cold start issues

Days to weeks of setup

With ComfyUI API

Export workflow JSON
Replace local paths with URLs
POST to /prompt endpoint

Done. Production-ready.

How It Works

Three steps. No configuration. No learning curve.

Export

Export your workflow JSON from ComfyUI. Use the built-in "Save (API Format)" option.

Replace

Replace local file paths with URLs. Models from HuggingFace, CivitAI, or your own storage.

POST

Send to our /prompt endpoint. Get results via webhook or poll for completion.

{
  "prompt": {
    "1": {
      "class_type": "CheckpointLoaderSimple",
      "inputs": {
        "ckpt_name": "https://huggingface.co/stabilityai/sdxl/resolve/main/sd_xl_base_1.0.safetensors"
      }
    },
    "2": {
      "class_type": "CLIPTextEncode",
      "inputs": {
        "text": "a beautiful sunset over mountains",
        "clip": ["1", 1]
      }
    },
    "3": {
      "class_type": "CLIPTextEncode",
      "inputs": {
        "text": "",
        "clip": ["1", 1]
      }
    },
    "4": {
      "class_type": "KSampler",
      "inputs": {
        "model": ["1", 0],
        "positive": ["2", 0],
        "negative": ["3", 0],
        "seed": 42,
        "steps": 20
      }
    }
  },
  "webhook_url": "https://your-app.com/webhook"
}

Everything You Need

Production-ready features that just work. No configuration required.

Native Format

Same JSON you already know from ComfyUI. Zero learning curve, zero format conversion.

Smart Routing

Jobs automatically route to nodes with your models already cached. Minimal cold starts.

Fair Queuing

No noisy neighbor problems. Every user gets fair access even during high demand.

Accurate Wait Times

Know how long your job will take before you commit. Data-driven predictions.

Webhook Delivery

Get results pushed to your server. Or poll if you prefer. Your choice.

50+ Node Packs

Popular extensions pre-installed. IPAdapter, ControlNet, AnimateDiff, and more.

8-20x cheaper than alternatives

Pay Only for What You Use

No subscriptions required. No idle costs. Just pay per second of GPU time.

Starting at

$0.000222/sec

RTX 4090 GPU time

No cold start billing
No minimum commitment
No hidden fees

View Full Pricing

Frequently Asked Questions

Everything you need to know to get started.

Ready to Ship Your Workflows?

Join the waitlist and get early access with $1 in free credits—enough for hundreds of images.

We'll never spam you