Model:
Price: from 60 credits per request · ≈ $0.03High stability with detailed usage records on the APIAny platform.
Use reference images
Leave off for text-to-image. Turn on to upload or paste up to 16 reference images.
Output size. Use auto, a W:H ratio, or a valid WIDTHxHEIGHT value; explicit pixels are preserved and must match the selected resolution tier.
Output resolution tier. It is independent from rendering quality.
Rendering effort. Auto lets the selected provider choose an appropriate tier.
Number of images to generate. Credits and upstream cost scale with n.
Background handling. Transparent output requires a compatible route.
Requested image output format when supported by the selected provider.
USD estimate ≈ $0.045: $999 tier: $1 = 2,000 credits.
Real image and video examples made through our models. Preview freely; using a preset never starts generation.
Actual generation model: gpt-image-2.5-flare
{
"model": "gpt-image-2.5",
"prompt": "Photorealistic editorial product photograph of a single unbranded cobalt-blue glass perfume bottle on a pale limestone plinth, soft side sunlight, delicate water caustics, subtle glass reflections, restrained luxury art direction, believable materials. Entire bottle visible with a generous margin, elegant wide composition. No text, letters, numbers, labels, branding, logos, watermark, interface, captions or graphic overlays anywhere in the image. One coherent scene, no collage.",
"size": "16:9",
"resolution": "2K",
"quality": "medium",
"n": 1,
"background": "opaque"
}History
Saved locally in this browser
0 running · 0 completed
Billing Rules
Authentication
Every request needs a Bearer token in the Authorization header. Create an API key in the console.
Authorization: Bearer YOUR_API_KEYhttps://apiany.ai/v1/images/generationsRequest parameters
| Parameter | Type | Required | Notes |
|---|---|---|---|
model | string | Required | Model identifier to invoke. Use this model's ID. |
prompt | string | Required | Text prompt describing what you want to generate. |
size | string | Optional | Output size. Use auto, a W:H ratio, or a valid WIDTHxHEIGHT value; explicit pixels are preserved and must match the selected resolution tier. · Options: auto, 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21 · Default: auto |
resolution | string | Optional | Output resolution tier. It is independent from rendering quality. · Options: 1K, 2K, 4K · Default: 1K |
quality | string | Optional | Rendering effort. Auto lets the selected provider choose an appropriate tier. · Options: auto, low, medium, high, xhigh, max · Default: auto |
n | number | Optional | Number of images to generate. Credits and upstream cost scale with n. · Range: 1–10 · Default: 1 |
background | string | Optional | Background handling. Transparent output requires a compatible route. · Options: auto, opaque, transparent · Default: auto |
output_format | string | Optional | Requested image output format when supported by the selected provider. · Options: png, jpeg, webp · Default: png |
output_compression | number | Optional | Compression level for JPEG or WebP output. · Range: 0–100 · Default: 100 |
callback_url | string | Optional | Optional webhook URL called when the async task finishes. |
Request example
curl "https://apiany.ai/v1/images/generations" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2.5",
"prompt": "Photorealistic editorial product photograph of a single unbranded cobalt-blue glass perfume bottle on a pale limestone plinth, soft side sunlight, delicate water caustics, subtle glass reflections, restrained luxury art direction, believable materials. Entire bottle visible with a generous margin, elegant wide composition. No text, letters, numbers, labels, branding, logos, watermark, interface, captions or graphic overlays anywhere in the image. One coherent scene, no collage.",
"size": "auto",
"resolution": "1K",
"quality": "auto",
"n": 1
}'Response example
{
"task_id": "task_abc123",
"status": "pending",
"poll_url": "/v1/tasks/task_abc123",
"request_id": "req_abc123",
"credits": {
"reserved": 1000
}
}This endpoint is asynchronous: it returns a task_id immediately. Poll the task-status endpoint until status becomes succeeded, then read the result. Generated media links stay valid for 24 hours.
