Percify APIFast, cheap image drafts
A prompt returns a draft in seconds for a few cents, before the final render. For tools that show many options quickly.
- Price
- $0.05 eachwith Z-Image Turbo
- You send
- a text prompt
- You get
- image
How it works
Send a text prompt
One POST to /run with the model id and your input. It answers at once with an id.
We run Z-Image Turbo
$0.05 each. Charged when it starts, refunded by itself if it fails.
Collect an image
GET /generations/{id}?wait=55 returns an image of what you described, as a file URL. Or pass a webhook and we call you.
3 models for this, by price
Prices are read from the live catalog. Each one opens the playground with this use case filled in.
The request
Filled in with sample files from our CDN, so it runs as it is. Swap in your own URLs.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "z-image-turbo",
"input": {
"prompt": "Close portrait of an elder with white chalk face paint and a flower crown, firelight"
}
}'Full reference in the docs. Every field Z-Image Turbo takes is on its model page.
Questions
What do I send to fast, cheap image drafts?
Send a text prompt in one POST to https://api.percify.io/v3/playground/v1/run. You get an image of what you described.
What does it cost?
With Z-Image Turbo it is $0.05 each (2 credits each). The picks on this page range from $0.05 each to $0.625 each. The estimate call returns the exact price of your input before you run it, and a run that fails is refunded.
Which model should I use?
Budget: Z-Image Turbo ($0.05 each). Balanced: GPT Image 2 (from $0.10). Premium: Nano Banana Pro ($0.625 each). Switching is one string in the request: the model id.
Can an AI agent do this for me?
Yes. Connect your agent to the MCP server at https://mcp.percify.io/mcp and ask for it in plain words. The agent calls the generate tool with the same model id and input shown on this page, and the call spends the same credits.
