Kling Omni-Image API

Kuaishou's Kling Omni-Image (omni-image endpoint). Text-to-image, single-image editing, multi-image fusion, batch up to 9. Two model versions: kling-image-o1 (1K/2K only) and kling-v3-omni (1K/2K/4K).

Authentication

Authorization: Bearer YOUR_API_KEY

Models & pricing

Model	model	Price	Notes
Kling Omni-Image (o1)	kling-image-o1	$0.0500/image	1K/2K, batch 1-9
Kling V3 Omni · 1K/2K	kling-v3-omni	$0.0500/image	1K/2K, batch 1-9
Kling V3 Omni · 4K	kling-v3-omni	$0.1000/image	4K tier

Code examples

# Step 1: Create task (text-to-image)
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-image-o1",
    "prompt": "A serene mountain lake at dawn, photorealistic",
    "resolution": "2k",
    "aspect_ratio": "16:9",
    "n": 1
  }'

# Multi-image input (image fusion)
curl -X POST https://api.apimodels.app/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-image-o1",
    "prompt": "Combine these two people into one scene",
    "image_urls": [
      "https://example.com/person1.jpg",
      "https://example.com/person2.jpg"
    ],
    "resolution": "2k"
  }'

# Step 2: Poll status
curl "https://api.apimodels.app/v1/images/generations?task_id=TASK_ID" \
  -H "Authorization: Bearer YOUR_API_KEY"

Request parameters

Field	Required	Type	Description
model	Yes	string	"kling-image-o1" (1K/2K) or "kling-v3-omni" (1K/2K/4K)
prompt	Yes	string	Text description or editing instructions
image_url	No	string	Single reference image URL for image editing
image_urls	No	string[]	Multiple reference image URLs for multi-image fusion
resolution	No	string	"1k" (default), "2k"; kling-v3-omni additionally supports "4k"
aspect_ratio	No	string	"1:1" (default), "16:9", "9:16", "4:3", "3:4"
n	No	integer	Batch size: 1-9 (default: 1)
callback_url	No	string	Webhook URL called when task completes

Notes

Both versions share this endpoint, switched via model: kling-image-o1 is 1K/2K only; kling-v3-omni supports up to 4K.
Priced by resolution: 1K/2K $0.05 per image; kling-v3-omni 4K $0.10 per image.
Use image_url for single-reference editing; image_urls (array) for multi-image fusion.
Batch n up to 9 images per request.

Try it in the Playground

FAQ

What is the difference between kling-image-o1 and kling-v3-omni?

Both share the same endpoint and features; kling-image-o1 outputs 1K/2K only, while kling-v3-omni additionally supports 4K (at a higher per-image price).

How is Kling Omni-Image priced?

By resolution: 1K/2K $0.05 per image; kling-v3-omni 4K $0.10 per image. Batch n multiplies the per-image price.