Video
kling-3.0 API
Use the exact kling-3.0 model ID through Modelflare asynchronous video routing.
Use the exact model ID kling-3.0. The model field must match this page exactly.
Parameters: duration=5resolution=1080pratio=16:9
Prompt: Stop-motion claymation style: a small orange clay fox sneaks through a miniature felt forest, pauses, sniffs a glowing mushroom and jumps back in surprise. Handmade textures, visible fingerprints on the clay, soft tabletop lighting, charming and playful, no text.
{ "model": "kling-3.0", "prompt": "Stop-motion claymation style: a small orange clay fox sneaks through a miniature felt forest, pauses, sniffs a glowing mushroom and jumps back in surprise. Handmade textures, visible fingerprints on the clay, soft tabletop lighting, charming and playful, no text.", "seconds": "5", "duration": 5, "resolution": "1080p", "ratio": "16:9", "aspect_ratio": "16:9"}Authentication and endpoint
Section titled “Authentication and endpoint”Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.
Authorization: Bearer YOUR_MODELFLARE_API_KEYCreate a task
Section titled “Create a task”curl https://modelflare.dev/v1/videos \ -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model_name": "kling-3.0", "prompt": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot", "duration": "5", "mode": "std" }'Poll and download
Section titled “Poll and download”Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.
curl https://modelflare.dev/v1/videos/TASK_ID \ -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"Request notes
Section titled “Request notes”Kling uses family-specific model_name, prompt, mode, duration, image_list, or contents / settings fields; native JSON is preserved and forwarded.
Request parameters
Section titled “Request parameters”Kling Legacy uses model_name with the text2video / image2video request structures. Check the model’s official page and pricing page for mode, resolution, and audio lanes.
| Field | Required | Notes |
|---|---|---|
model_name |
Yes | kling-3.0 |
prompt |
Conditional | Required for text-to-video; combine with images for image-to-video |
image |
Conditional | First-frame image URL or Base64 |
image_tail |
No | Optional end-frame image |
video_url |
Conditional | Reference video for Kling 3.0 motion control |
image_list |
No | Image list for Omni/O1 and multimodal workflows |
negative_prompt |
No | Negative prompt |
mode |
No | std / pro / 4k (model-dependent) |
duration |
No | 3–15 seconds (string) |
multi_shot |
No | Enable multi-shot storyboarding |
sound |
No | Generate synchronized sound where supported |
camera_control |
No | Camera control where supported |
Input and output limits
Section titled “Input and output limits”Kling Legacy requests use model_name; availability of mode, duration, image / image_tail, sound, and camera_control depends on the model. Minimum billable seconds and resolution lanes follow the per-model rows on the pricing page.
Documented workflow examples
Section titled “Documented workflow examples”Legacy models select model_name, first/end-frame, or motion-control fields by workflow; fixed duration and audio limits follow this page’s table.
curl https://modelflare.dev/v1/videos \ -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model_name": "kling-3.0", "prompt": "转移动作并保持人物身份", "image": "https://example.com/character.png", "video_url": "https://example.com/motion.mp4", "duration": "5", "mode": "std" }'Errors and failed tasks
Section titled “Errors and failed tasks”Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.
Supported scope
Section titled “Supported scope”This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.
Pricing and billing
Section titled “Pricing and billing”This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.
Media contract · v1
Official source: Kuaishou Kling
Contract parameters
| Intent field | Control | Options |
|---|---|---|
ratio | select | 16:9 / 9:16 / 1:1 |
resolution | select | 720p / 1080p / 4k |
duration | select | 3 / 5 / 8 / 10 / 15 |
audio | switch | — |
Supported capability
allowed_values·ratio· 16:9, 9:16, 1:1allowed_values·resolution· 720p, 1080p, 4kallowed_values·duration· 3, 5, 8, 10, 15max_assets·reference_asset_ids· 2
Structured request example
text
Intent
{
"audio": false,
"duration": 3,
"prompt": "A red paper kite over a quiet harbour at dusk.",
"ratio": "16:9",
"resolution": "720p"
}Provider request
{
"aspect_ratio": "16:9",
"duration": "3",
"mode": "std",
"model_name": "kling-3.0",
"prompt": "A red paper kite over a quiet harbour at dusk.",
"sound": "off"
}reference
Intent
{
"audio": false,
"duration": 3,
"prompt": "A red paper kite over a quiet harbour at dusk.",
"ratio": "16:9",
"resolution": "720p"
}Provider request
{
"aspect_ratio": "16:9",
"duration": "3",
"image": "https://example.com/reference.png",
"mode": "std",
"model_name": "kling-3.0",
"prompt": "A red paper kite over a quiet harbour at dusk.",
"sound": "off"
}