Add Uncensored Image Generation to Your App in 5 Minutes

This is the shortest path from nothing to a working uncensored image generation call. No SDK, no polling loop, no infrastructure. If you can make an HTTP request, you can finish this in about five minutes.

1. Get a key (1 min)#

1. Sign up with an email — no card needed.
2. Open API keys and create one. It looks like api18_xxxxxxxxxxxxxxxx.
3. Export it: export API18_KEY=api18_...

2. Make the call (2 min)#

One endpoint does everything: POST /v1/generate?wait=true. Send a model id (from the models page) and a prompt. The prompt isn’t filtered.

curl -X POST "https://api18.dev/v1/generate?wait=true" \
  -H "Authorization: Bearer $API18_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<image-model-id>",
    "prompt": "your prompt here"
  }'

# → returns the finished job; the image URL is at .data[0].url

3. Use the result (1 min)#

The response is the finished job. Read the image URL from data[0].url and you’re done. The job also tells you cost_usd and when the file expires_at — download it if you need to keep it.

Let an AI write it for you#

Even faster: open Build with AI, copy the ready-made prompt (it bundles the full reference), and paste it into ChatGPT, Claude, Cursor or Gemini. Then just say what you want and it writes the integration against the real endpoints and model ids.

Free to start#

New accounts get $10 in free credit to test models in the playground. For the API, top up paid balance in USDT on Solana or Tron — see signing up and paying with crypto.