Quick Start

Call your first model API

The fastest path is: sign in, create an API key, confirm available models, then send a protected request.

01
Sign in and open the console.
02
Create a project API key under Settings > API Keys.
03
Check the public model catalog.
04
Send a protected chat, image, or video request.

List models

curl https://devnextapiany.mexxxxai.win/api/v1/models

Chat completion

curl https://devnextapiany.mexxxxai.win/api/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "user", "content": "Say hello in one sentence." }
    ],
    "max_tokens": 128
  }'

Image task

curl https://devnextapiany.mexxxxai.win/api/v1/images/generate \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A clean dashboard for API cost governance",
    "size": "1024x1024"
  }'

What to check next

Open Settings > Usage to review request ids, credit charges, latency, and errors.
Use Admin > API Models, API Channels, and API Costs to control catalog, routing, and upstream cost rules.
Run POST /api/internal/jobs/process-pending-media from your scheduler to process async media tasks, and check-stale-media-tasks to refund timed-out work.