SeeDance 2.0 API pricing: cost per second and the cheapest route

Seedance 2.0 starts at $0.022 per second on UnificAlly for Mini 480p requests that include a reference video. The clearest direct-price saving is Pro 1080p text-to-video: $0.31/sec on UnificAlly, below BytePlus's published direct rate. Pick Mini for the lowest entry cost, Fast for a speed-oriented route, or Pro for 1080p and 4K.

TL;DR: Seedance 2.0 comes in Mini, Fast, and Pro routes. Current prices run from $0.022/sec to $0.741/sec, based on variant, resolution, and whether a reference video is present. Output runs 4–15 seconds with native audio and up to nine images, three videos, and three audio references. Mini is the lowest-cost draft route; Pro adds 1080p and 4K. Check the live rate card before a large batch.

What is SeeDance 2.0?

SeeDance 2.0 is ByteDance's flagship video model, released in early February 2026. The public API beta opened on April 14, 2026. It accepts a text prompt plus an optional multimodal reference set, and returns a 4 to 15 second MP4 with synchronized audio, at 480p or 720p on Mini and Fast and from 720p up to 4K on Pro.

Three things make it different from SeeDance 1.5 Pro:

• Multimodal omni-reference. Up to nine reference images, three videos, and three audio tracks per call, addressable in the prompt with placeholders.
• Native audio-video generation. Audio is generated jointly with the video (not as a post-process), with millisecond lip-sync across multiple languages.
• Multi-shot storytelling. Multiple connected shots in a single generate call, with the same character recognisable across them.

ByteDance also reports a 31.7-point physics benchmark improvement over SeeDance 1.5 Pro, mostly on water, cloth, and gravity simulation.

What's new in SeeDance 2.0

The biggest shift is that the prompt surface stops being a bottleneck. Before SeeDance 2.0, multi-asset creative briefs ("a video that combines the look of this still, the motion of this video, and the audio mood of this track") had to be split into multiple generations and stitched together. SeeDance 2.0 takes the whole brief in one call.

The other shift is multi-shot output with character consistency. Earlier video models would render a multi-shot prompt as four separate-looking generations stitched together. SeeDance 2.0 holds the character (face, body, clothing) across shots in the same generate, which closes the biggest gap between AI video and proper short-form narrative work.

What you can do with SeeDance 2.0

Three variants on UnificAlly

• Seedance 2.0 Mini: lowest-cost route, at 480p or 720p.
• Seedance 2.0 Fast: speed-oriented route, at 480p or 720p.
• Seedance 2.0 Pro: the quality route, at 720p, 1080p, or 4K.

All three use the same task API and 4–15 second duration range. Mini and Fast output 480p or 720p. Pro outputs 720p, 1080p, or 4K.

Modes

• Text-to-video. A prompt is enough.
• First and last frame. Supply first_frame_url, last_frame_url, or both; SeeDance 2.0 fills in the motion.
• Omni-reference. Up to nine images, three videos, and three audio tracks, addressable via @Image1, @Video1, @Audio1 placeholders in the prompt.

Inputs

• prompt. Required.
• images. Up to 9 reference images.
• videos. Up to 3 reference videos.
• audio. Up to 3 reference audio tracks.
• duration. 4 to 15 seconds.
• resolution. 480p or 720p on Mini and Fast; 720p, 1080p, or 4k on Pro.
• aspect_ratio. 16:9, 9:16, 1:1, 4:3.
• audio: false. Disable audio output for a silent MP4.
• seed. Optional, for reproducibility.

Output

• MP4 at 24 FPS: 480p or 720p on Mini and Fast, 720p up to 4K on Pro.
• Native synchronized audio (unless disabled).
• Returned via task-based async polling.

Which Seedance 2.0 variant should you use?

Both variants expose the same parameters. Pick by what the workload needs.

The rate depends on resolution and reference-video input, not only the model name. Use the exact row below when estimating a batch.

SeeDance 2.0 pricing and how it compares

These are our current per-second rates. A request containing a reference video can use a different price from text-to-video or image-only input.

Where UnificAlly is cheaper than BytePlus direct

UnificAlly is not cheaper than BytePlus's published Seedance 2.0 Pro text-to-video rates on every resolution. The clearest saving is the 1080p route, where our per-second rate sits below BytePlus's direct one. The BytePlus reference-video examples use a different input-duration formula, so they are not an equivalent per-output-second comparison. Source: BytePlus Seedance 2.0 pricing.

Run Seedance 2.0 Pro at $0.31/sec for 1080p.

How to call SeeDance 2.0 on UnificAlly

The API is async: POST a generation, then poll the task endpoint until the MP4 is ready.

Text-to-video, multi-shot, with omni-reference

const API = 'https://api.unifically.com';
const headers = {
  Authorization: `Bearer ${process.env.UNIFICALLY_API_KEY}`,
  'Content-Type': 'application/json',
};

const start = await fetch(`${API}/v1/tasks`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    model: 'bytedance/seedance-2.0-pro',
    input: {
      prompt:
        'Shot 1: the chef in @Image1 plates the dish from @Image2 in a sunlit kitchen. Shot 2: she walks the plate to the dining room. Shot 3: she serves a guest, who smiles. Soundtrack matches the mood of @Audio1.',
      aspect_ratio: '16:9',
      duration: 15,
      images: ['https://example.com/chef.jpg', 'https://example.com/dish.jpg'],
      audio: ['https://example.com/jazz-mood.mp3'],
    },
  }),
}).then((r) => r.json());

while (true) {
  await new Promise((r) => setTimeout(r, 3000));
  const task = await fetch(`${API}/v1/tasks/${start.data.task_id}`, { headers }).then((r) => r.json());
  if (task.data.status === 'completed') {
    console.log(task.data.output.video_url);
    break;
  }
  if (task.data.status === 'failed') throw new Error(task.data.error_message);
}

First-and-last-frame mode

const start = await fetch(`${API}/v1/tasks`, {
  method: 'POST',
  headers,
  body: JSON.stringify({
    model: 'bytedance/seedance-2.0-pro',
    input: {
      mode: 'first_last_frame',
      prompt: 'A slow rotation of the product, soft rim lighting, marble plinth',
      duration: 6,
      first_frame_url: 'https://example.com/product-front.jpg',
      last_frame_url: 'https://example.com/product-three-quarter.jpg',
    },
  }),
}).then((r) => r.json());

Switching to Fast

Same payload, swap the model id to bytedance/seedance-2.0-fast.

Working with omni-reference

Omni-reference is the differentiator, so it is worth calling out directly.

• Address references by placeholder. In the prompt, write @Image1, @Image2, @Video1, @Audio1 to point a sentence at a specific reference asset. The model ties that clause to that file slot.
• Order matters. images[0] becomes @Image1, images[1] becomes @Image2, and so on. Same for videos[] and audio[]. Reorder the array if you want a different placeholder mapping.
• Don't max out the slots by default. Three to five well-chosen images plus one source video almost always beats nine mixed images. References compete for influence; loading too many dilutes the strongest one.
• Audio references shape mood, not literal output. Pass an audio track and SeeDance 2.0 tries to match its mood, tempo, and feel, not splice the video into the output. Use it the way you would use a "vibe reference" in a brief.

Things to know about SeeDance 2.0

• Expecting 1080p or 4K from Mini or Fast. Both stop at 720p. Draft on Mini or Fast, lock the seed, and move the keeper to SeeDance 2.0 Pro when the shot needs 1080p, 4K, or Pro's quality.
• Treating Pro and Fast as different feature surfaces. They expose the same modes and reference surface; the split is output quality, speed, resolution range, and per-second price. Choose based on output quality needs and latency budget.
• Stuffing all 15 omni-reference slots. Three to five well-chosen references usually beat fifteen mixed ones. Send the minimum that anchors the look.
• Forgetting audio: false for silent runs. Audio is generated by default. If the downstream pipeline replaces the audio anyway, pass audio: false to keep generation focused.
• Confusing duration with shot count. Duration is the total video length (4 to 15 seconds). Multi-shot narrative is a prompt-structure decision (Shot 1: ... Shot 2: ...). You can have 15 seconds of single-shot content or 15 seconds split across three or four shots.

SeeDance 2.0 FAQ

What is SeeDance 2.0?

SeeDance 2.0 is ByteDance's February 2026 flagship video model. It accepts a text prompt plus up to nine reference images, three reference videos, and three reference audio tracks, and returns a 4 to 15 second MP4 with synchronized audio, at 480p or 720p on Mini and Fast and up to 4K on Pro. Multi-shot narrative output with character consistency works in a single call.

How much does Seedance 2.0 cost?

On UnificAlly, Seedance 2.0 ranges from $0.022/sec for Mini 480p with a reference video to $0.741/sec for Pro 4K without one. Pro 1080p text-to-video is $0.31/sec, below BytePlus's published direct rate. Check the pricing page for the current rates.

What is omni-reference?

Omni-reference is SeeDance 2.0's multimodal input surface: up to nine images, three videos, and three audio tracks per generation. Each asset is addressable in the prompt via placeholders (@Image1, @Video1, @Audio1), so each clause maps to a specific file slot.

What is the difference between Seedance 2.0 Mini, Fast, and Pro?

Mini has the lowest entry price, Fast is the speed-oriented route, and Pro is the quality route. Mini and Fast output 480p or 720p, and Pro outputs 720p, 1080p, or 4K. All use the same asynchronous task API and support 4–15 second output.

Does SeeDance 2.0 generate audio?

Yes. Audio is generated jointly with the video in the same pass, with millisecond lip-sync across multiple languages. Pass audio: false to disable audio output and return a silent MP4.

Related reading on SeeDance 2.0

• SeeDance 2.0 model page: live Pro and Fast playgrounds.
• Veo 3.1 vs SeeDance 2.0: Western flagship comparison.
• SeeDance 2.0 vs Kling 3.0: Chinese flagship comparison.
• Kling 3.0 and MiniMax Hailuo: other video APIs to consider.
• Suno pricing guide: what full-track music for your SeeDance 2.0 videos costs, per plan or per API request.