Cost level
~½ of Standard
Official positioning: ~50% lower generation cost vs Standard
The Seedance 2.0 Mini model costs approximately half of the standard‑version model, runs twice as fast as the Fast variant, supports 480P/720P output, and is suitable for batch and large‑scale production. The current version is the full‑power version of the Seedance 2.0 Mini model, which supports real‑human subjects and human faces.
$ Official original price based on Token billing,unit: $/million tokens:
limited‑time 60% off now
Seedance 2.0 Mini Reference Material Mode supports 9 reference images, 3 reference videos and 3 audio materials. Real‑human subjects and human faces are supported, with automatic content moderation! Material and Scene Restrictions Text Prompts: Chinese prompts are recommended to be no more than 500 characters, and English prompts no more than 1000 words. Image Input: Supports jpeg, png, webp, bmp, tiff, gif, heic, heif; each image must be less than 30 MB, with an aspect ratio ranging from 0.4 to 2.5, and pixel dimensions between 300px and 6000px for both width and height. No more than 9 items for multimodal reference scenes. Video Input: Supports mp4, mov; each video clip ranges from 2 to 15 seconds, with a maximum of 3 reference videos and a combined total duration of no more than 15 seconds for all videos; each video must be less than 50 MB; frame rate ranges from 24 to 60 fps. Audio Input: Supports wav, mp3; each audio segment ranges from 2 to 15 seconds, with a maximum of 3 reference audio clips and a combined total duration of no more than 15 seconds for all audio; each audio segment must be less than 15 MB. Audio cannot be imported alone; at least one reference image or video must be provided alongside audio input. 🔸Note🔸: With video input has a lower unit price due to a different calculation method: No video = Price × Output; With video = Price × (Input + Output).
Seedance 2.0 Image to Video‘s Mini Version Model.
Seedance 2.0 mini is a new-generation cost-effective video generation model developed to meet broader video generation demands. While maintaining competitive performance, it brings video generation capabilities to application scenarios featuring lower entry barriers, higher frequency of use and larger-scale deployment. This is a text to video model.
Official lineup · Seedance 2.0 Mini
About half of Standard's cost, 2× faster than Fast, quality on par with Fast.
Mini is built for scale: e-commerce assets, batch marketing content, short-drama b-roll, UGC effects. 480P / 720P output with 720P clips from about $0.35 per 5s — the lowest unit price to run high-volume pipelines.
Cost level
~½ of Standard
Official positioning: ~50% lower generation cost vs Standard
Speed
2× faster than Fast
The fastest tier in the lineup, made for high-frequency calls
Quality
On par with Fast
Official positioning: output quality comparable to Fast
720P unit price
≈ $0.07 / sec
Pay-as-you-go; live rates on the APIPod pricing page
Within the family, Mini pushes per-clip cost to the floor and throughput to the ceiling.
Reference prices for a 5s 16:9 clip; token-based billing, successful tasks only. Always refer to live rates on Volcano Ark and the APIPod pricing page.
| Unit: USD per 1M tokens (no video reference input) | 5s 16:9 per-clip reference price |
|---|---|
| Mini · 480P | $3.2 / 5s ≈ $0.17 |
| Mini · 720P | $3.2 / 5s ≈ $0.35 |
| Fast · 720P | $5.1 / 5s ≈ $0.55 |
| Standard · 720P | $6.4 / 5s ≈ $0.69 |
1080P / 4K remain Standard-only; always refer to live rates on Volcano Ark and the APIPod pricing page.
Cheap, but no toy: full task coverage and native audio.
Text-to-video, image-to-video, reference generation, and video editing are all supported.
Native audio output with synced voice-over and music (lip-sync verified in hands-on tests).
Up to 6 images + 3 videos + 3 audios as references to lock subjects and style.
Output tops out at 480P / 720P; switch model to seedance-2.0 or seedance-2.0-fast for higher quality.
Demos from the official Seedance 2.0 launch blog — Mini shares the family's task system, and these are exactly the scenarios where its unit cost shines.
I2V · E-commerce ad
Image-to-video plus a story brief yields a ready-to-ship ad with captions and voiceover — Mini's unit price makes batch ad creative truly viable.
Official prompt
The man in the painting nervously peeks out of the frame, grabs a cola, and drinks with pure satisfaction. Footsteps approach — he slips it back as a cowboy walks off with it. End on a top-lit cola close-up against pure black, artistic captions and VO: 'Cola you can't resist!'
T2V · Sensory close-up
Delicate sounds and hand close-ups generated in one pass — classic high-share UGC material, ideal for templated volume output.
Official prompt
Immersive first-person ASMR. Close-up under warm soft light: slender hands gently trigger frosted glass scratches, plush fabric rubs, acrylic taps, and bubble-wrap squeezes. Slow, gentle motion, natural trigger sounds only, relaxing mood.
T2V · Effects play
Syncopated footwork and flying fringe physics stay stable throughout — great for effects templates and content formats at scale.
Official prompt
1920s jazz-club Charleston. A dancer in a gold fringe dress and a partner in a pinstripe suit perform at high intensity: syncopated footwork, aerial lifts, wide arm swings. Dynamic tracking shots with foot close-ups; fringe whips with every kick, vintage film-grain atmosphere.
Batch-generate candidate assets at the lowest unit cost.
Keep the winners based on conversion or human review.
Send hero content to seedance-2.0 for 1080P / 4K masters.
Just change the model field — billing, observability, and retries carry over.
Example request
Same API as Standard — set model to seedance-2.0-mini.
Parameter names may vary by provider channel and model revision. Use your live APIPod model docs as the source of truth.
curl -X POST https://api.apipod.ai/v1/videos/generations \
-H "Authorization: Bearer $APIPOD_API_KEY" \
-H "Content-Type: application/json" \
-d {
"model": "seedance-2.0-mini",
"prompt": "E-commerce product showcase: a smartphone slowly rotating under soft lighting, clean background, upbeat music.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true
}Officially, output quality is comparable to Fast — the trade-off is the 480P/720P resolution cap. That's plenty for e-commerce and asset workloads; polish hero content on Standard.
Yes. At launch ByteDance stated Mini generates 2× faster than Seedance 2.0 Fast at roughly half of Standard's cost — positioned for cost-efficient, high-volume production.
Yes — officially up to 6 images + 3 videos + 3 audios per request, useful for locking character looks, scenes, and style.
Batch e-commerce assets, marketing content at scale, UGC effects, and short-drama b-roll — anything high-volume and cost-sensitive.
One integration on APIPod — Mini, Fast, and Standard are just a model field apart.