Type
Spec
Rate
Standard 720p
per second
$0.157
Standard 1080p
per second
$0.235
Video input 720p
per second of input plus output, at least twice the output
$0.094
Video input 1080p
per second of input plus output, at least twice the output
$0.141
Kling 4.0 and Kling V3 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Kling AI Video GenerationKling 4.0 and Kling V3 are both Kling AI models in the Video Generation category, available through the EmpirioLabs API.
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Kling 4.0 | Kling V3 |
|---|---|---|
| prompt | string | string |
| resolution | 720p, 1080p Default: 1080p | - |
| aspect_ratio | 16:9, 9:16, 1:1, 21:9 Default: 16:9 | 16:9, 9:16, 1:1 Default: 16:9 |
| duration | 3 to 30 Default: 5 | 3 to 15 Default: 5 |
| image | string | string |
| image_end | string | - |
| middle_images | string | - |
| reference_images | string | - |
| video | string | - |
| reference_videos | string | - |
| model_tier | - | standard, pro, 4k Default: standard |
| sound | - | boolean Default: true |
| negative_prompt | - | string |
Generates 3 to 30 second clips at 24 fps in 720p or 1080p, each with a native stereo audio track.
One attached image is the first frame, two are the first and last frames, and three or more are references. The first attached video is the one edited; any others are references.
Model tiers: standard renders 720p, pro renders 1080p, 4k renders 3840x2160. Durations run 3 to 15 seconds. Native audio is on by default; turning Sound off bills the lower rate on standard and pro, while 4K includes audio at one flat rate. Image-to-video accepts one or two images (first and last frame) and follows the source image size.
Kling 4.0 runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to kling-4-0 or kling-v3. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-4-0",
"prompt": "Describe what you want Kling 4.0 to generate."
}'Kling 4.0 is the newer release (Oct 15, 2026); Kling V3 was released on Feb 5, 2026. Input types only Kling 4.0 accepts: Video. Capabilities listed only for Kling 4.0: editing. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Kling 4.0 is the newer release (Oct 15, 2026); Kling V3 was released on Feb 5, 2026.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/videos/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.