AI Image
Image generation overview — one unified endpoint, multiple models
All image models share one endpoint — POST /api/v2/image/generate — and differ only by the
model field. Text-to-image or reference-guided. Async task; poll for status after submitting.
Base URL:
https://api.aiclonevoicefree.com｜ Auth:Authorization: Bearer sk_...
Models
| Model | model id | Best for | Ref images | Billing |
|---|---|---|---|---|
| GPT Image | gpt-image-2 (default) | Photoreal, prompt-faithful, image edit | up to 4 | 3 credits / image |
| Gemini Flash Image | gemini-3.1-flash-image-preview | Fast, multi-reference compositing | up to 14 | 3 credits / image |
Both are flat 3 video credits per image (independent of size / reference images;
nis fixed to 1).
Shared request
| Field | Type | Required | Notes |
|---|---|---|---|
prompt | string | ✅ | Text prompt |
model | string | ⬜ | One of the model ids above, default gpt-image-2 |
size | string | ⬜ | Aspect/size, default 1:1 (e.g. 1:1 / 16:9 / 9:16) |
image_urls | string[] | ⬜ | Reference images (image-to-image / edit) |
seed | int | ⬜ | Random seed |
curl -X POST https://api.aiclonevoicefree.com/api/v2/image/generate \
-H "Authorization: Bearer sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{ "prompt": "a corgi under cherry blossoms, cinematic", "model": "gpt-image-2", "size": "16:9" }'Response 202
{ "task_id": "xxxxxxxx", "status": "pending", "capability": "image", "action": "generate", "model": "gpt-image-2" }Getting the result
Poll GET /api/v2/tasks/{task_id}; when done:
{
"status": "completed",
"capability": "image",
"_type": "image.generate",
"imageUrl": "https://.../result.png"
}See Tasks for polling cadence and the unified response format. Insufficient credits →
402(withrequired/balance) at submit; auto-refunded on failure.