API Hop

Seedance 2.0 multimodal reference video API

Create Seedance 2.0 video from image or video references, with optional audio references, on API Hop. At least one image or video is required.

Seedance 2.0 online multimodal reference tool

Model settings

Sign in to run with your account balance.

Pricing and billing

Seedance 2.0 requests and examples

Recorded with Seedance 2.0 on 2026-10-03. One sample, not a quality or latency guarantee.

View prompt

Premium beverage product film, one continuous five-second shot. A single tall clear glass filled with sparkling orange citrus drink and clear ice cubes stands on a pale gray stone pedestal, a small lemon wedge on the left and one green leaf on the right, clean muted turquoise studio background. Soft daylight from upper left glints through the glass. The camera makes a slow, subtle clockwise orbit while keeping the entire glass centered. Tiny bubbles rise naturally and condensation glistens. Preserve the glass shape and orange drink color throughout. No cuts, no hands, no text, no logos, no music, no speech. Silent video.

{
  "model": "seedance-2.0",
  "duration": 5,
  "resolution": "720p",
  "aspectRatio": "16:9",
  "generateAudio": false,
  "prompt": "Premium beverage product film, one continuous five-second shot. A single tall clear glass filled with sparkling orange citrus drink and clear ice cubes stands on a pale gray stone pedestal, a small lemon wedge on the left and one green leaf on the right, clean muted turquoise studio background. Soft daylight from upper left glints through the glass. The camera makes a slow, subtle clockwise orbit while keeping the entire glass centered. Tiny bubbles rise naturally and condensation glistens. Preserve the glass shape and orange drink color throughout. No cuts, no hands, no text, no logos, no music, no speech. Silent video.",
  "metadata": {
    "content": []
  }
}

Recorded with Seedance 2.0 on 2026-10-03. One sample, not a quality or latency guarantee.

View prompt

Create one continuous five-second product shot from the supplied first frame to the supplied last frame. Keep the camera locked, with exactly the same clear glass, ice cubes, stone pedestal, lemon wedge, green leaf, turquoise background and soft upper-left lighting. A thin stream of orange citrus drink pours naturally from above the top edge into the glass. The liquid level gradually rises from the first-frame level to the last-frame level; the ice floats upward slightly, bubbles and ripples behave naturally. The pouring stream stops before the end and the final image settles into the supplied last-frame composition. No cuts, no new objects, no hands, no text, no logos. Silent video, no music or speech.

{
  "model": "seedance-2.0",
  "duration": 5,
  "resolution": "720p",
  "aspectRatio": "16:9",
  "generateAudio": false,
  "prompt": "Create one continuous five-second product shot from the supplied first frame to the supplied last frame. Keep the camera locked, with exactly the same clear glass, ice cubes, stone pedestal, lemon wedge, green leaf, turquoise background and soft upper-left lighting. A thin stream of orange citrus drink pours naturally from above the top edge into the glass. The liquid level gradually rises from the first-frame level to the last-frame level; the ice floats upward slightly, bubbles and ripples behave naturally. The pouring stream stops before the end and the final image settles into the supplied last-frame composition. No cuts, no new objects, no hands, no text, no logos. Silent video, no music or speech.",
  "metadata": {
    "content": [
      {
        "type": "image_url",
        "role": "first_frame",
        "image_url": {
          "url": "https://api.apihop.ai/generated/364459846248173568/0.png"
        }
      },
      {
        "type": "image_url",
        "role": "last_frame",
        "image_url": {
          "url": "https://api.apihop.ai/generated/364460494205222912/0.png"
        }
      }
    ]
  }
}

Recorded with Seedance 2.0 on 2026-10-03. One sample, not a quality or latency guarantee.

View prompt

Use the supplied reference image to preserve the exact clear highball glass, orange citrus drink, ice, stone pedestal, lemon wedge and green leaf. Use the reference video only for its slow clockwise camera orbit and soft lighting rhythm. Create a fresh five-second premium beverage product shot in the same muted turquoise studio setting. Begin with the whole glass centered, make a small smooth clockwise orbit and finish slightly closer while retaining the entire glass. Keep the liquid level and glass shape consistent with the image; tiny bubbles rise naturally. One continuous shot, no cuts, no added objects, no text, no logos. Silent video, no music or speech.

{
  "model": "seedance-2.0",
  "duration": 5,
  "resolution": "720p",
  "aspectRatio": "16:9",
  "generateAudio": false,
  "prompt": "Use the supplied reference image to preserve the exact clear highball glass, orange citrus drink, ice, stone pedestal, lemon wedge and green leaf. Use the reference video only for its slow clockwise camera orbit and soft lighting rhythm. Create a fresh five-second premium beverage product shot in the same muted turquoise studio setting. Begin with the whole glass centered, make a small smooth clockwise orbit and finish slightly closer while retaining the entire glass. Keep the liquid level and glass shape consistent with the image; tiny bubbles rise naturally. One continuous shot, no cuts, no added objects, no text, no logos. Silent video, no music or speech.",
  "metadata": {
    "content": [
      {
        "type": "image_url",
        "role": "reference_image",
        "image_url": {
          "url": "https://api.apihop.ai/generated/364460494205222912/0.png"
        }
      },
      {
        "type": "video_url",
        "role": "reference_video",
        "video_url": {
          "url": "https://api.apihop.ai/examples/seedance-2-0/2026-10-03/364460440891424768-text-to-video.mp4"
        }
      }
    ]
  }
}

Request and input example only; this request has no recorded output.

View prompt

Premium beverage product film, one continuous five-second shot. A single tall clear glass filled with sparkling orange citrus drink and clear ice cubes stands on a pale gray stone pedestal, a small lemon wedge on the left and one green leaf on the right, clean muted turquoise studio background. Soft daylight from upper left glints through the glass. The camera makes a slow, subtle clockwise orbit while keeping the entire glass centered. Tiny bubbles rise naturally and condensation glistens. Preserve the glass shape and orange drink color throughout. No cuts, no hands, no text, no logos, no music, no speech. Silent video.

{
  "model": "seedance-2.0",
  "duration": 5,
  "resolution": "720p",
  "aspectRatio": "16:9",
  "generateAudio": false,
  "prompt": "Premium beverage product film, one continuous five-second shot. A single tall clear glass filled with sparkling orange citrus drink and clear ice cubes stands on a pale gray stone pedestal, a small lemon wedge on the left and one green leaf on the right, clean muted turquoise studio background. Soft daylight from upper left glints through the glass. The camera makes a slow, subtle clockwise orbit while keeping the entire glass centered. Tiny bubbles rise naturally and condensation glistens. Preserve the glass shape and orange drink color throughout. No cuts, no hands, no text, no logos, no music, no speech. Silent video.",
  "metadata": {
    "content": [
      {
        "type": "image_url",
        "role": "first_frame",
        "image_url": {
          "url": "https://api.apihop.ai/generated/364459846248173568/0.png"
        }
      }
    ]
  }
}

Seedance 2.0 API pricing and billing

480p · With video reference

Official price

Completion tokens
$4.0000 /M

API Hop price Save 5%

Completion tokens
$3.8000 /M

480p · Without video reference

Official price

Completion tokens
$6.5714 /M

API Hop price Save 5%

Completion tokens
$6.2429 /M

720p · With video reference

Official price

Completion tokens
$4.0000 /M

API Hop price Save 5%

Completion tokens
$3.8000 /M

720p · Without video reference

Official price

Completion tokens
$6.5714 /M

API Hop price Save 5%

Completion tokens
$6.2429 /M

1080p · With video reference

Official price

Completion tokens
$4.4286 /M

API Hop price Save 5%

Completion tokens
$4.2071 /M

1080p · Without video reference

Official price

Completion tokens
$7.2857 /M

API Hop price Save 5%

Completion tokens
$6.9214 /M

4k · With video reference

Official price

Completion tokens
$2.2857 /M

API Hop price Save 5%

Completion tokens
$2.1714 /M

4k · Without video reference

Official price

Completion tokens
$3.7143 /M

API Hop price Save 5%

Completion tokens
$3.5286 /M

Reference price - not independently verified. Check the publisher's current rates, billing units and applicable terms before comparing costs.

Seedance 2.0 multimodal references

Create Seedance 2.0 video from image or video references, with optional audio references, on API Hop. At least one image or video is required.

Multimodal references: inputs and settings

Select the media that actually supports the brief. More references are not automatically better when they contain conflicting subjects, camera paths or sound.

Images for appearance, video for movement

A reference image can guide the subject or visual treatment; a reference video can guide movement or camera behavior. Describe which appearance and which movement should contribute to the new clip. The available media roles include reference_image, reference_video and reference_audio.

Audio references and generated audio are different controls

An audio reference is an input; generated audio is an output setting controlled separately. Describe what the reference sound should contribute. Audio cannot be the only media input: provide at least one image or video alongside it.

Keep within the 9 / 3 / 3 media limits

The complete request allows at most 9 images, 3 videos and 3 audio references. Native typed media and shorthand fields count together, not as separate allowances. Use public HTTP(S) URLs or existing asset:// IDs; this form does not upload local media.

The output uses a fixed integer duration of 4-15 seconds, independent of the reference clip length. Resolution options are 480p, 720p, 1080p and 4k; aspect ratios are 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 and adaptive. Generated audio is optional.

Joint audiovisual generation and output review

Seedance 2.0 can generate sound alongside the image sequence, supporting exploration of ambience, action effects and dialogue in short shots. Generated audio is an output setting; audio-reference inputs depend on the selected mode, so native multimodal capability does not mean every page accepts every media type.

Multimodal references: reviewing the output

Evaluate video quality against real inputs and the intended use. The checks below focus on observable output, not a promise that a demonstration or single example predicts quality, latency or business success.

Reference contribution and subject consistency

Evaluate each reference against its assigned role: appearance from the image, movement from the video, and sound characteristics from the audio. Check that the result does not accidentally borrow an unwanted subject, background or camera action from another reference.

Conflicting inputs and sound alignment

Review camera direction, action timing and audio events together. When references disagree, remove unnecessary media or clarify the priority in the prompt. More inputs do not guarantee better control, and a successful task does not establish exact reproduction of the source.

Explain how the references work together

Describe the subject, the reference contribution and the requested change in one coherent brief. For a product image and a camera reference video, ask to keep the product recognizable while adapting the camera movement. Review the resulting motion and sound rather than assuming exact reproduction.

For a new scene without existing media, use text-to-video. For a defined starting composition and optional ending image, use the first and last frame mode. These tasks share the model but need different inputs.

Record total duration, rework and actual cost

Use a consistent task set to record submission-to-result time, revision count and account charges. Distinguish waiting, task completion and human acceptance. Establish an acceptable quality and budget before increasing volume, rather than treating one wait as a stable service-speed estimate.

API request and job tracking

Submit the current mode's request to POST /v1/video/seedance, then query GET /v1/jobs/{jobId} with the returned job ID. Wait for COMPLETED with output before using the result; checking an existing task does not require submitting another generation.

Seedance 2.0 multimodal references FAQ

Does the reference video determine the output duration?

No. Select the output duration explicitly as an integer from 4 to 15 seconds. A reference video is a media input, not an automatic-duration setting or a promise to reproduce the entire source clip.

Is any existing asset:// ID usable?

It must refer to media already available to the provider account used for the request. This page does not create or upload those assets. A syntactically valid ID alone does not prove that the selected channel can access the media.

Can Seedance 2.0 use an audio reference by itself?

No. This mode requires at least one image or video reference. Audio is an optional additional input, while generateAudio separately controls generated sound in the output. Supplying audio does not replace the visual-input requirement.

How do I tell Seedance 2.0 what each reference should contribute?

Specify the subject, desired motion and the role of each input in one brief. Use the ordered image, video and audio references to distinguish assets, and describe what to preserve or borrow from each. An asset ID is a media address, not an instruction about how to use it.

Do the four Seedance 2.0 pages use different model parameters?

No. All four input modes use model: seedance-2.0, submit an asynchronous video task to POST /v1/video/seedance, and query GET /v1/jobs/{jobId}. Do not substitute a page mode, display name or another model ID for the API model value.

Which durations and output settings does Seedance 2.0 support?

The current API Hop interface uses integer durations from 4 to 15 seconds, defaulting to 5. Resolutions are 480p, 720p, 1080p and 4k; ratios are 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 and adaptive. Generated audio is separate. Do not use -1 for automatic duration or add seed, negativePrompt or other undocumented parameters.

How should I troubleshoot authentication, balance or generation errors?

Check Bearer authentication, balance, seedance-2.0 model access and the required inputs for the selected mode, then verify media accessibility. Retain the full error and job ID, and distinguish submission failure, a pending job and task failure instead of inferring the cause from one numeric code.

How can I confirm the cost of Seedance 2.0 generation?

Check pricing for the resolution, duration and presence of video input in this page's pricing section, then confirm actual charges against account records. An unavailable price does not mean free generation; do not apply another version's rates or text-model pricing to this video task.

Other video modes

Related video APIs