Seedance 2.0 Mini

Seedance 2.0 Mini is the lower-priced tier of ByteDance's Seedance 2.0, which fal describes as a faster version that keeps strong performance at a lower cost. On fal it has text-to-video and image-to-video endpoints with an optional last frame, 4 to 15 seconds (or auto), 480p or 720p in seven aspect ratios, and synchronized audio, including lip-synced speech, on by default at no extra charge. Like the rest of the family it is billed per token, at $0.007 per 1,000, half the full model's rate.

Anvisha Pai

Anvisha Pai, Co-founder & CEO, Voyager

Tested

ByteDance

Seedance 2.0 Mini filming itself as seed lantern on a river, generated by us.
›What we asked for

A self-portrait of Seedance 2.0 Mini, ByteDance's cinematic video model: a paper lantern shaped like a seed drifts over a night river in a Chinese water town, its light rippling on the water, slow dolly, native ambient sound of water and distant music.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

At a glance

Price
$0.007 per 1,000 tokens on fal, half Seedance 2.0's rate, read October 22, 2026. A five-second 720p clip at the 1280 by 720 we got back is 108,000 tokens, $0.756; fal rounds it to about $0.1547 a second.
Measured wait
147 to 458 seconds from queue submission to a five-second 720p clip, across nine prompts in one batch. Not a service guarantee.
Length
4 to 15 seconds, or auto; 480p or 720p only.
Audio
Sound effects, ambience and lip-synced speech, on by default; fal charges the same with it off.
Inputs
Text, or a first frame with an optional last frame to transition to.

Other Seedance models: Seedance 2.0, Seedance 2.5. Compare all 3.

Anvisha's take

Seedance 2.0 Mini made the best title card of this batch and took the longest to do it. 'MODA SUMMER SESSIONS' sits in tangerine on a navy bar exactly as the prompt asked, with 'Friday 12 June' correct underneath, over a sunset festival crowd. The speaking woman is natural and ends on a warm smile, the pour keeps the kettle, the paper filter and a glass server intact, and the market has the busker and a golden retriever on its lead. The look is Seedance's at half the price: our nine clips cost $0.756 each against $1.52 on Seedance 2.0. It is not faster in practice: clips took 147 to 458 seconds, where Seedance 2.0 took 88 to 148. And it changes products. The turntable dripper grew a handle halfway round, and in image-to-video our handleless dripper grew one too while water poured onto the grounds. I would use it for type and people when waiting is fine, not for product shots. These are frame-based observations; audio was present on every clip but not scored by ear.

Seedance 2.0 Mini real output: the same 9 clips every model gets

Every video model on this site gets the same 9 clips, so you can compare like with like. These are the clips Seedance 2.0 Mini returned, one try each, nothing re-rolled or retouched. Each tile shows one frame of the clip until you press play. Generated on . The 9 clips took 147 to 458 seconds each and cost $6.80 in total.

Product turntable5s clip · 147s wait · $0.756

A clean product shot that holds its shape through a full slow rotation.

›What we asked for

A matte black ceramic pour-over coffee dripper rotating slowly on a white turntable, soft studio light, seamless white background, product video, no text.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Person speaking5s clip · 179s wait · $0.756

A face, lip sync and a spoken line, where the model makes audio.

›What we asked for

A woman in her 40s with short grey hair stands in a bright kitchen, looks at the camera and says 'Good morning, the coffee is ready', natural window light, handheld feel, she smiles at the end.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Animated title card5s clip · 421s wait · $0.756

Set text that stays spelled correctly while it moves.

›What we asked for

A title card reading 'MODA SUMMER SESSIONS' animates in over slow-motion footage of a festival crowd at dusk, then a smaller line 'Friday 12 June' fades in beneath it. Bold condensed type, tangerine on navy.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Camera move5s clip · 370s wait · $0.756

A steady drone push-in with stable geometry.

›What we asked for

Drone shot pushing slowly forward over a coastal town at sunrise, terracotta roofs, fishing boats in the harbour, long shadows, cinematic and steady.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Physics5s clip · 458s wait · $0.756

A spill in slow motion: does water behave like water.

›What we asked for

A glass of water tips over on a wooden table and spills in slow motion, water and three ice cubes sliding across the wood, macro lens, morning light.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Hands at work5s clip · 354s wait · $0.756

Hands, a kettle and a steady pour without extra fingers or teleporting objects.

›What we asked for

Close-up of hands pouring hot water from a gooseneck kettle in slow circles into a pour-over coffee dripper, steam rising, shallow depth of field, warm cafe light.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Busy scene5s clip · 167s wait · $0.756

Many people and objects moving at once without merging.

›What we asked for

A crowded Saturday farmers market seen from slightly above, shoppers with tote bags, a dog on a leash, a busker with a guitar, bunting swaying, late morning light, gentle camera drift.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Specific art style5s clip · 261s wait · $0.756

A named style held across every frame rather than drifting to photoreal.

›What we asked for

A lighthouse on a rocky cliff in a storm, in the style of a Japanese ukiyo-e woodblock print, waves crashing in flat colour with visible wood grain, animated like moving paper cutouts.

bytedance/seedance-2.0/mini/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

Image to video5s clip · 287s wait · $0.756

Bring a still product photo to life without changing the product.

›What we asked for

The coffee dripper slowly fills as coffee drips through it, steam rising, the camera drifting gently around it, the dripper itself unchanged. (starting from The Nano Banana Pro product shot from the image fixture set.)

bytedance/seedance-2.0/mini/image-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5, generate_audio: true
returned 1280 by 720 pixels

How the cost under each picture was worked out: fal's Seedance 2.0 Mini rate (fal model page, read 2026-10-22): $0.007 per 1,000 tokens, tokens = height x width x seconds x 24 / 1024, at the measured 1280x720 for 5 seconds; fal does not return the charge.

Compare Seedance 2.0 Mini

Seedance 2.0 Mini pricing

WhereUnitPriceSource
fal1,000 tokens
Tokens = height x width x seconds x 24 / 1024, the same rate at 480p and 720p and on image-to-video. fal's own per-second figures: about $0.0721 at 480p and $0.1547 at 720p.
$0.007fal model page, read
falFive-second 720p clip
What our clips cost at the measured 1280 by 720; see the cost basis under each one.
$0.756fal model page, read
VoyagerSecond at 720p
About 11.3 credits a second at 720p, 1 credit for 1¢. On every paid plan; Free has no video.
$0.1134Voyager pricing, read

Is Seedance 2.0 Mini free?

The fal endpoints are paid per token. We have not found a free allowance for Mini on fal.

  • •The Seedance 2.0 page covers Dreamina's free daily credits for the family's consumer app.

fal model page, read

Where to use Seedance 2.0 Mini

  • fal, text-to-video · Hosted API and playground; the endpoint used for eight of the clips below.
  • fal, image-to-video · First frame plus an optional last frame; used for the image-to-video clip.
  • Voyager · Runs inside Voyager, the agent for creative work, on Voyager credits on every paid plan, or with your own fal key.

Voyager

Run Seedance 2.0 Mini inside Voyager

Voyager is an agent for creative work that runs every model in this reference, Seedance 2.0 Mini included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.

What we noticed running Seedance 2.0 Mini

  • •Tangerine type on a navy bar exactly as asked, both lines spelled correctly, the date set smaller in italics beneath. See the animated title card clip.
  • •Water pours onto grounds in our photographed dripper, which then grows a mug handle for the second half. See the image to video clip.
  • •A spiral-ribbed dripper with a paper filter in it turns cleanly, then gains a handle halfway round. See the product turntable clip.
  • •The tumbler tips and the water pools with two cubes sliding out, but late in the shot the glass hangs tilted in the air. See the physics clip.
  • •Hand, gooseneck kettle, paper filter, white dripper and glass server all intact; the kettle carries a small invented logo. See the hands at work clip.

Seedance 2.0 Mini limits and API parameters

LimitValue
Duration4 to 15 seconds, or auto; 480p or 720p, no 1080p.
fal API schema, read
Output sizeEvery clip came back at 1280 by 720, 24 frames a second, 5.11 seconds long, including the square product photo we asked for at 16:9.
fal API schema, read
›Every setting, for developers

fal (bytedance/seedance-2.0/mini/text-to-video)

fal API schema, read

ParameterTypeValuesDefault
promptstringFree text
Required.
durationenumauto, 4 to 15
Sent as a string.
auto
resolutionenum480p, 720p720p
aspect_ratioenumauto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16auto
generate_audiobooleantrue, false
The price is the same either way.
true
codecenumauto, H264, H265auto

Seedance 2.0 Mini image-to-video

fal API schema, read

ParameterTypeValuesDefault
image_urlURLJPEG, PNG, WebP and more, up to 30 MB
Required; the first frame.
end_image_urlURLImage
Optional; the clip transitions to it.

What Seedance 2.0 Mini will not make

ByteDance's models run behind fal's safety checker and fal's partner terms. None of our nine prompts was refused, including the product photo Seedance 2.5 declined. The Seedance 2.0 page covers the family's history with studio likeness complaints.

fal model page, read

Alternatives to Seedance 2.0 Mini

Frequently asked questions

How much does Seedance 2.0 Mini cost?

$0.007 per 1,000 tokens on fal, read October 22, 2026, where tokens are height times width times seconds times 24 over 1,024. A five-second 1280 by 720 clip is 108,000 tokens, $0.756, half what Seedance 2.0 costs. In Voyager it is about 11.3 credits a second at 720p.

Is Seedance 2.0 Mini faster than Seedance 2.0?

Not in our run. fal describes Mini as faster, but our nine clips took 147 to 458 seconds, against 88 to 148 for Seedance 2.0 in an earlier batch. Queue time is included, so a quieter day could differ.

What does Seedance 2.0 Mini give up?

1080p (it stops at 720p), and on our prompts, product fidelity: it added a handle to the dripper in both the text and the image clip. The text card, people and pour held up.

How this page is made

Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.

Anvisha Pai

Anvisha Pai

Co-founder & CEO, Voyager

Anvisha is the CEO of Voyager and a repeat, Y Combinator-backed startup founder. She was previously a PM at Dropbox. She believes nobody should need a design degree to make something that looks great.