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.
Next-generation Seedance built for long-form storytelling: one request can produce a coherent clip of up to 30 seconds, draw on up to 50 reference assets, and edit or extend existing footage.
Modes
Text to video, first frame, or first and last frame.
Multimodal reference to video from up to 30 images, 10 videos, and 10 audio clips. Audio-only input works on its own.
To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording.
Output
480p, 720p, 1080p, and 4K at 24fps, 4 to 30 seconds, with native synchronized audio.
4K is 3840x2160 at 16:9 and is encoded as 10-bit H.265/HEVC, which some players cannot open.
MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it.
When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio.
Draft mode
Set draft to true to render a 480p draft while you are still trying shots. Drafts render at 480p only.
The response returns the draft's id as usage.draft_task_id. Send that back as draft_task_id to render the same shot at 1080p, or at 4K with resolution set to 4k.
The final render takes the prompt, reference assets, duration, aspect ratio, seed and audio setting from the draft, so only resolution, output_format and return_last_frame apply alongside draft_task_id. A draft stays promotable for 14 days.
Input limits
Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each.
Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each.
Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each.
Uploaded images and videos that show a real person's face are blocked. To feature a person, start from an image made with Seedream 5.5. To use your own face, verify it in My face.
Billing
Without a reference video, you are billed per second of generated video at the rate for the output resolution.
With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone.
Draft mode is not a discounted rate. A draft bills as a normal 480p generation and its final bills as a normal generation at the final's resolution, 1080p or 4K, so the saving comes from trying shots at 480p and rendering only your pick.
Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate.
Uploaded media preprocessing
Video inputs are capped to 30 seconds.
Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched.
Kling O3
Video model in Standard or Pro modes with text-to-video, image-to-video, reference-to-video, editing, native sound, and multi-scene transitions.
Uploaded media preprocessing
Video inputs are capped to 10 seconds for video-edit and video-reference workflows.
Uploaded video inputs are normalized to provider-compatible MP4 when needed.
Kling O3 4K supports text, image, and image-only reference workflows. Use Standard or Pro for video inputs.
How to call Seedance 2.5 and Kling O3
Seedance 2.5 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 seedance-2-5 or kling-o3. Get an API key from the EmpirioLabs dashboard.
cURL: submit the job
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5",
"prompt": "Describe what you want Seedance 2.5 to generate."
}'
Seedance 2.5 vs Kling O3: tests and guides
Prompt tests and comparison runs that cover both models.
What is the difference between Seedance 2.5 and Kling O3?
Seedance 2.5 is the newer release (Aug 7, 2026); Kling O3 was released on Feb 5, 2026. Capabilities listed only for Seedance 2.5: text to video, image to video, reference to video, video editing, multimodal, audio sync. Capabilities listed only for Kling O3: audio, editing. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Which is newer, Seedance 2.5 or Kling O3?
Seedance 2.5 is the newer release (Aug 7, 2026); Kling O3 was released on Feb 5, 2026.
Which has the lower rate, Seedance 2.5 or Kling O3?
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.
Can I switch between Seedance 2.5 and Kling O3 without rebuilding my integration?
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.
Can I try Seedance 2.5 and Kling O3 in the browser before integrating?
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.