
Long-form video model for coherent clips up to 30 seconds, with up to 50 reference images, videos, and audio clips, native audio, editing, and extension.
Long-form video model for coherent clips up to 30 seconds, with up to 50 reference images, videos, and audio clips, native audio, editing, and extension.
Also known as ByteDance Seedance 2.5
seedance-2-5/v1/videos/generationsbytedance/seedance-2.5seedance-2.5Outputs from our published tests. Each one links to the post it comes from.
From Seedance 2.5 vs Seedance 2.0 Pro vs Kling V3 vs Kling O3: Which 4K Video API to Use
From Seedance 2.5 Flash vs Seedance 2.5 vs Seedance 2.0 Fast: Which Seedance Video API to Use
Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.
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. 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": "seedance-2-5",
"prompt": "Describe what you want Seedance 2.5 to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/videos/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "seedance-2-5",
"prompt": "Describe what you want Seedance 2.5 to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)Request parameters supported by the Seedance 2.5 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| prompt | string | - | - | Scene description. Address a specific attachment inline as @Image1, @Video1, or @Audio1 to say which reference a shot should follow. |
| mode | enum | auto | auto, t2v, i2v_first, i2v_both, reference | Selects how your inputs are used. auto detects it from what you attach. t2v is text to video. i2v_first animates a first frame. i2v_both animates between a first and... |
| resolution | enum | 720p | 480p, 720p, 1080p, 4k | Output resolution. 4K is 3840x2160 at 16:9 and is encoded as 10-bit H.265/HEVC, which some players cannot open. Draft mode always renders at 480p, so this is ignored... |
| aspect_ratio | enum | adaptive | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 | Output aspect ratio. adaptive lets the model choose. With a first frame, the video always follows that image's aspect ratio. Editing an attached video keeps that... |
| custom_duration | boolean | true | - | If false, the model decides clip length. |
| duration | number | 5 | 4 to 30 | Clip length in seconds. Only used when custom_duration=true. Video editing always keeps the source clip length, and the clip being edited must be 4 to 30 seconds long. |
| generate_audio | boolean | true | - | Generate native audio with the video. |
| output_format | enum | mp4 | mp4, mov | mp4 plays everywhere. mov carries higher color precision for color grading, keying, and compositing, and some players cannot open it. |
| draft | boolean | false | - | Render a 480p draft to try the shot cheaply, then render the one you like at native 1080p or 4K from the same prompt, references and seed. |
| draft_task_id | string | - | - | The ID of a draft to render at native 1080p, or at 4K with resolution set to 4k. The draft keeps its prompt, references, length, aspect ratio, seed and audio. Drafts... |
| return_last_frame | boolean | false | - | Also return the final frame as an image, ready to use as the first frame of the next clip. |
| image | string | - | - | Reference / first-frame image URL. |
| image_end | string | - | - | End-frame image URL for i2v_both. |
| video | string | - | - | Reference video URL for reference / edit / extend. |
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.
Announcements, prompt tests, and comparisons that cover this model.
API Access How to Use the Seedance 2.5 API Seedance 2.5 generates coherent video up to 30 seconds in a single request, accepts up to 50 reference images, videos,...
API Access How to Use Seedance 2.5 Draft Mode: Draft at 480p, Finish in 4K Seedance 2.5 Draft Mode on EmpirioLabs: try a shot as a 480p draft, then render the one you pick at 1080p or in native 4K...
API Access How to Generate 4K Video with Seedance 2.5 Seedance 2.5 now renders native 4K on EmpirioLabs: 3840x2160 clips of up to 30 seconds with native audio, and Draft Mode...On EmpirioLabs, Seedance 2.5 is billed pay as you go: T2V/I2V 480P $0.206 per second; T2V/I2V 720P $0.462 per second; T2V/I2V 1080P $1.137 per second; T2V/I2V 4K $1.827 per second; Video Input 480P $0.123 per second of input plus output; Video Input 720P $0.276 per second of input plus output; Video Input 1080P $0.680 per second of input plus output; Video Input 4K $1.128 per second of input plus output. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.
Seedance 2.5 takes Text, Image, Video, Audio as input and returns Video.
Seedance 2.5 supports 480p, 720p, 1080p, 4K. The default is 720p, and the parameter reference lists any limits by resolution.
Seedance 2.5 is served through POST /v1/videos/generations on api.empiriolabs.ai with standard bearer-token authentication.
Send seedance-2-5 as the model in your request. The alternate IDs bytedance/seedance-2.5, seedance-2.5 also work.
ByteDance released Seedance 2.5 on Aug 7, 2026.
Seedance 2.5 on EmpirioLabs is served from Malaysia.
Yes. The EmpirioLabs playground runs Seedance 2.5 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.
Check out our pricing or reach out if you want your own model deployed on our stack.