Seedance 2.0 Mini API
AI VideoSeedance 2.0 Mini is the cheapest Seedance route on OmniaKey, id dreamina-seedance-2-0-mini-260615: text to video, first-frame and reference generation at 480P or 720P, for up to 15 seconds per job.
- Per second of output$0.02–$0.04
- OperationsText to video
- Image to video
- Reference to video
- View tool pricing and billing rules
Your result will appear here once you run the model.
01
Where it fits
Seedance 2.0 Mini is the cheapest Seedance route on OmniaKey, id dreamina-seedance-2-0-mini-260615: text to video, first-frame and reference generation at 480P or 720P, for up to 15 seconds per job.
Pick Seedance 2.0 Mini for drafts and high-volume passes at $0.02 to $0.04 per second, then re-render the winners on a larger tier; a 4-second 480P clip came back in about 100 seconds in our record.
02
What it does
Text to video
dreamina-seedance-2-0-mini-260615
Generate a short video clip from a text prompt.
Image to video
dreamina-seedance-2-0-mini-260615
Animate a still image into a short video clip.
Reference to video
dreamina-seedance-2-0-mini-260615
Guide a clip with reference media to keep a subject, style or motion.
03
In depth
Seedance 2.0 Mini, id dreamina-seedance-2-0-mini-260615, is the least costly way to make a Seedance clip on this catalog. It runs text to video, first-frame animation and reference-based shots, produces 480P or 720P output, and accepts durations from 4 to 15 seconds.
Think of it as the drafting bench. Nothing it makes is meant to be the final master: 1080P is not on the menu, and the other two 2.0 ids cover the same operations at higher rates when the picture matters. What it does offer is a wide, repeated look at how a prompt behaves without a large bill attached.
Our 14 September 2026 smoke run pushed one job of each kind through it at 480p for 4 seconds, and all three returned 864x496 H.264 files of 4.04 seconds. Those results, plus a probe that tried to send audio as the only reference, are recorded below.
Cheap iteration on a beat
Render the same eight-second beat twenty times to find the take that holds together, then re-render the winner on 2.0 or 2.5. At 480P the grid is quick to scan and the differences show up as timing and framing rather than fine texture.
Animating a mood board
Turn each still on a look-dev board into a short moving clip so a director can feel the pacing. Supply the still as first_frame, describe only the motion, and keep to 480P until the sequence is locked.
Reference-based exploration
Try a character or package against five different settings with one reference image repeated. The September run shows an inlined reference at 480p is accepted, which is enough to judge whether a design reads at small size before commissioning a master.
04
Hands-on notes
Our 14 September 2026 smoke run rendered a 4-second 480p Seedance 2.0 Mini text-to-video job as an 864x496 H.264 MP4 of 4.04 seconds.
The Seedance 2.0 Mini image-to-video job in that run took an inlined first frame at 4 seconds and 480p and returned an H.264 MP4.
Seedance 2.0 Mini reference-to-video returned an 864x496 MP4 of 4.04 seconds.
A Seedance 2.0 Mini reference request with only audio and no image or video reference failed instead of starting a job.
05
Limits to plan around
- The resolution menu holds two entries, 480P and 720P. A large-frame deliverable has to move to Seedance 2.0 or 2.5, and an accepted draft cannot be scaled up by this id afterwards.
- Durations run 4 to 15 seconds. If a shot needs to breathe past that, the job has to be cut in two or handed to Seedance 2.5.
- Expect an audio track on the output, as on every Seedance id, and write the sound into the prompt if you want it to fit the picture.
- The catalog places this id below Fast at both resolutions, but the difference shows up on long jobs, not on a single four-second test.
06
Compare nearby models
| Model | Best for | Operations | Listed price |
|---|---|---|---|
| Seedance 2.0 MiniThis page dreamina-seedance-2-0-mini-260615 | The lowest rate in the family for drafts at 480P or 720P. | Text to video · Image to video · Reference to video | $0.02–$0.04 per second |
| Seedance 2.0 Fast dreamina-seedance-2-0-fast-260128 | Same two resolutions and the same operations, listed one step up at each tier. | Text to video · Image to video · Reference to video | $0.03–$0.06 per second |
| Seedance 2.0 dreamina-seedance-2-0-260128 | Adds 1080P and a higher ceiling on picture quality for final renders. | Text to video · Image to video · Reference to video | $0.077–$0.407 per second |
07
Sources and verification
Guide updated 2026-10-27.
08
Call it
Media models run asynchronously. Create a task, poll it until it finishes, then download the signed asset URL.
# 1. Create the job. 202 Accepted; the body carries the task id,
# the pre-charged price, and a poll_url. Reuse one Idempotency-Key
# across retries so a timeout never starts a second paid job.
curl --fail-with-body https://api.omniakey.com/v1/media/tasks \
-H "Authorization: Bearer $OMNIAKEY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: dreamina-seedance-2-0-mini-260615-001" \
-d '{
"model": "dreamina-seedance-2-0-mini-260615",
"type": "video",
"operation": "text_to_video",
"input": {"prompt": "a paper boat on a quiet lake at sunset"},
"parameters": {"duration": 6, "resolution": "720p"}
}'
# 2. The same model id and the same poll loop serve the other operations:
# image_to_video media[] type "first_frame"
# reference_to_video media[] type "reference_image"
# Reference media travel alongside the prompt:
# {"prompt": "...", "media": [{"type": "first_frame", "url": "https://example.com/first-frame.png"}]}
# A public HTTPS URL or a base64 data URI both work.
# 3. Poll GET /v1/media/tasks/{id} until status is
# succeeded | failed | canceled. Progress carries percent and stage.
curl --fail-with-body https://api.omniakey.com/v1/media/tasks/TASK_ID \
-H "Authorization: Bearer $OMNIAKEY_API_KEY"
# 4. Download assets[0].url before expires_at, or poll again for a
# fresh signed URL. Failed and canceled jobs are refunded.
curl -sS -o out.mp4 "$(jq -r '.assets[0].url' result.json)"09
Pricing
Video jobs are billed per second of rendered output, not per token. Failed or canceled jobs are refunded automatically.
$0.02–$0.04per secondSave 50%
- 480P
- $0.02per second
- 720P
- $0.04per second
More models from ByteDance
Related articles
HappyHorse 1.1 vs Seedance 2.0: Same-Prompt Test and Price
Same three prompts, same day: Seedance 2.0 made the better clips, HappyHorse 1.1 made them twice as fast.
Read articleSeedance 2.5 Prompt Guide: Structure, Examples and Real Clips
Six prompts, six real clips: what Seedance 2.5 followed, what it changed and how to fix it.
Read articleKling 3.0 vs Seedance 2.5
Both models are live on OmniaKey and both can serve the same brief. One is billed once per generation from a mode and duration matrix, the other per output second by resolution — and only one of them accepts a reference-driven shot.
Read articleBest AI video API models in 2026
There is no single best video model. The right route depends on whether you need a long shot, a faithful first frame, reference images, predictable cost, or a faster production queue.
Read articleFrequently asked questions
How do I call Seedance 2.0 Mini on OmniaKey?
POST to /v1/media/tasks with the model id, type "video", and operation "text_to_video" — or "image_to_video" with a first frame in input.media[] with type "first_frame". Reuse one Idempotency-Key across retries so a timeout never starts a second paid job.
What does Seedance 2.0 Mini cost?
Seedance 2.0 Mini bills $0.02–$0.04 per second of rendered video. Creation pre-charges the requested duration up front from your prepaid balance, and failed or canceled jobs are refunded automatically.
Why does the API return a task id instead of the video?
Video renders take from about a minute to several minutes, so OmniaKey runs every video route through one asynchronous lifecycle. Poll GET /v1/media/tasks/{id} until the status is succeeded, then read the signed asset URL.
Is Seedance 2.0 Mini good enough for a final deliverable?
It tops out at 720P, so it suits social, previews and internal review more than broadcast. Plenty of work ships at 720P; the honest test is to render one shot here and the same shot on Seedance 2.0, then look at them side by side on the target screen.
Does Mini support reference images like the other tiers?
Yes. reference_to_video takes reference_image entries in input.media, and the September smoke run passed one inlined at 480p and got a normal clip back. A request with audio as its only reference is refused, so include at least one image or video.
How is a Mini job billed?
Per output second at 480P or 720P, taken from balance when the task is created and returned if the task fails. The current rate is in the price table on the model page. Because duration is chosen in whole seconds, a 6-second draft and a 6-second master differ only by the resolution tier.
What prompt style works on this generation?
Shot numbering, not timestamps. ByteDance's guide reports that the 2.0 generation follows labels such as Shot 1 and Shot 2, while 2.5 reads time ranges. Keep each block to one action and one camera move, and the small frame will still read clearly.
Can a Mini draft be finished on a higher tier?
Only by rendering it again, since the file itself cannot be upscaled by this service. Keep the prompt, the seed frame and the duration identical and change just the model id and resolution, so the two versions differ in sharpness rather than in content.
