Seedance video API: models, fields and media requirements
Connect to Seedance with a BetterToken API Key and choose fields, media and generation methods by Model ID and operation.
Generate videos from text, a first frame or reference media. The four China-region models support three generation operations; the two SR models support text-to-video and single-first-frame image-to-video. Choose a Model ID by operation, duration and output level.
Prepare your BetterToken API Key. The Base URL is https://bettertoken.ai/v1, with Authorization: Bearer YOUR_API_KEY for authentication. Copy the Model ID exactly, including capitalization.
Every request.json below follows the same workflow: quote, confirm creation, poll and download. A quote does not start generation; creating a task submits a paid request. See current costs in the model plaza.
Models and operations
The table below lists available values by operation. See each subsection for field defaults, media counts and combination constraints. Media sizes use 1 MB = 1048576 bytes.
| Model ID | Operation | Duration (seconds) | Output level | Aspect ratio | Audio | Media roles |
|---|---|---|---|---|---|---|
ByteDance-Seedance-2.0-SR | image_to_video | 5–10, step 5 | 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | first_frame |
ByteDance-Seedance-2.0-SR | text_to_video | 5–10, step 5 | 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
ByteDance-Seedance-2.5-SR | image_to_video | 5–10, step 5 | 720p, 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | first_frame |
ByteDance-Seedance-2.5-SR | text_to_video | 5–10, step 5 | 720p, 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
doubao-seedance-2-0-260128 | image_to_video | 4–15, step 1; supports auto | 480p, 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | first_frame, last_frame |
doubao-seedance-2-0-260128 | reference_to_video | 4–15, step 1; supports auto | 480p, 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | reference_image, reference_video, reference_audio |
doubao-seedance-2-0-260128 | text_to_video | 4–15, step 1; supports auto | 480p, 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
doubao-seedance-2-0-fast-260128 | image_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | first_frame, last_frame |
doubao-seedance-2-0-fast-260128 | reference_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | reference_image, reference_video, reference_audio |
doubao-seedance-2-0-fast-260128 | text_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
doubao-seedance-2-0-mini-260615 | image_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | first_frame, last_frame |
doubao-seedance-2-0-mini-260615 | reference_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | reference_image, reference_video, reference_audio |
doubao-seedance-2-0-mini-260615 | text_to_video | 4–15, step 1; supports auto | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
doubao-seedance-2-5-260628 | image_to_video | 4–30, step 1; supports auto | 480p, 720p, 1080p | adaptive | on, off | first_frame, last_frame |
doubao-seedance-2-5-260628 | reference_to_video | 4–30, step 1; supports auto | 480p, 720p, 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | reference_image, reference_video, reference_audio |
doubao-seedance-2-5-260628 | text_to_video | 4–30, step 1; supports auto | 480p, 720p, 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | on, off | None |
The two SR models support only 5 or 10 seconds for fixed duration. China-region and SR models have different Model IDs. Do not apply one model’s field or media limits to another model.
Sample media
The image-to-video and image-reference examples use a blue ceramic mug on a white table. Keep the sample image to try them, or first replace it with public HTTPS media that you have the right to use and that meets this page’s limits.

Text-to-video
ByteDance-Seedance-2.0-SR
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed | fixed |
duration.seconds | integer | No | 5–10, step 5 s; only for fixed duration | 5 |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | 16:9 |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 720p, 1080p, 4k | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "ByteDance-Seedance-2.0-SR", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
ByteDance-Seedance-2.5-SR
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed | fixed |
duration.seconds | integer | No | 5–10, step 5 s; only for fixed duration | 5 |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | 16:9 |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 720p, 1080p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "ByteDance-Seedance-2.5-SR", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
doubao-seedance-2-0-260128
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p, 4k | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto".
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-260128", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
doubao-seedance-2-0-fast-260128
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto".
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-fast-260128", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
doubao-seedance-2-0-mini-260615
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto".
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-mini-260615", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
doubao-seedance-2-5-260628
Use this operation when you have only a text description.
Set model to this subsection’s Model ID and operation to text_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | auto |
duration.seconds | integer | No | 4–30, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
This operation does not accept media.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto".
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-5-260628", "operation": "text_to_video", "prompt": "A blue ceramic mug on a white table. Slowly move the camera closer in soft daylight.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "16:9" }}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
Image-to-video
ByteDance-Seedance-2.0-SR
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed | fixed |
duration.seconds | integer | No | 5–10, step 5 s; only for fixed duration | 5 |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | 16:9 |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 720p, 1080p, 4k | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp | size at most 10 MB; width 128–4096 px; height 128–4096 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- You must provide
first_frame.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "ByteDance-Seedance-2.0-SR", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
ByteDance-Seedance-2.5-SR
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed | fixed |
duration.seconds | integer | No | 5–10, step 5 s; only for fixed duration | 5 |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | 16:9 |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 720p, 1080p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp | size at most 10 MB; width 128–4096 px; height 128–4096 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- You must provide
first_frame.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "ByteDance-Seedance-2.5-SR", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-0-260128
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p, 4k | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
last_frame | image, optional, at most 1 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - You must provide
first_frame.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-260128", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-0-fast-260128
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
last_frame | image, optional, at most 1 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - You must provide
first_frame.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-fast-260128", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-0-mini-260615
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
last_frame | image, optional, at most 1 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - You must provide
first_frame.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-mini-260615", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-5-260628
Use this operation to set the opening frame or both the first and last frames with images.
Set model to this subsection’s Model ID and operation to image_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | auto |
duration.seconds | integer | No | 4–30, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
first_frame | image, 1 (required) | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
last_frame | image, optional, at most 1 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - You must provide
first_frame. - This operation requires
output.aspect_ratio="adaptive", whether you supply only the first frame or both the first and last frames.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-5-260628", "operation": "image_to_video", "prompt": "Slowly move the camera closer to the blue ceramic mug. Preserve its shape and the white table.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "first", "type": "image", "role": "first_frame", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
Reference generation
doubao-seedance-2-0-260128
Use this operation to preserve subject or motion characteristics from reference media.
Set model to this subsection’s Model ID and operation to reference_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p, 4k | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
reference_image | image, optional, at most 9 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
reference_video | video, optional, at most 3 | mp4, mov | size at most 200 MB; width 300–6000 px; height 300–6000 px; duration 2–15 s; frame rate at least 24 fps, and at most 60 fps; total for this role at most 15 s |
reference_audio | audio, optional, at most 3 | wav, mp3 | size at most 15 MB; duration 2–15 s; total for this role at most 15 s |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - Provide at least one of these roles:
reference_image,reference_video,reference_audio. - Reference audio cannot be used alone. Also provide a reference image or reference video.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-260128", "operation": "reference_to_video", "prompt": "Create a product video of the blue ceramic mug in the reference image. Keep its shape and color.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "reference", "type": "image", "role": "reference_image", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-0-fast-260128
Use this operation to preserve subject or motion characteristics from reference media.
Set model to this subsection’s Model ID and operation to reference_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
reference_image | image, optional, at most 9 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
reference_video | video, optional, at most 3 | mp4, mov | size at most 200 MB; width 300–6000 px; height 300–6000 px; duration 2–15 s; frame rate at least 24 fps, and at most 60 fps; total for this role at most 15 s |
reference_audio | audio, optional, at most 3 | wav, mp3 | size at most 15 MB; duration 2–15 s; total for this role at most 15 s |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - Provide at least one of these roles:
reference_image,reference_video,reference_audio. - Reference audio cannot be used alone. Also provide a reference image or reference video.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-fast-260128", "operation": "reference_to_video", "prompt": "Create a product video of the blue ceramic mug in the reference image. Keep its shape and color.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "reference", "type": "image", "role": "reference_image", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-0-mini-260615
Use this operation to preserve subject or motion characteristics from reference media.
Set model to this subsection’s Model ID and operation to reference_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | fixed |
duration.seconds | integer | No | 4–15, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
reference_image | image, optional, at most 9 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
reference_video | video, optional, at most 3 | mp4, mov | size at most 200 MB; width 300–6000 px; height 300–6000 px; duration 2–15 s; frame rate at least 24 fps, and at most 60 fps; total for this role at most 15 s |
reference_audio | audio, optional, at most 3 | wav, mp3 | size at most 15 MB; duration 2–15 s; total for this role at most 15 s |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - Provide at least one of these roles:
reference_image,reference_video,reference_audio. - Reference audio cannot be used alone. Also provide a reference image or reference video.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-0-mini-260615", "operation": "reference_to_video", "prompt": "Create a product video of the blue ceramic mug in the reference image. Keep its shape and color.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "reference", "type": "image", "role": "reference_image", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
doubao-seedance-2-5-260628
Use this operation to preserve subject or motion characteristics from reference media.
Set model to this subsection’s Model ID and operation to reference_to_video. Use only the generation fields listed below. Put media in the media array.
| Field | Type | Required | Allowed values or range | Default |
|---|---|---|---|---|
audio.mode | string | No | on, off | on |
duration.mode | string | No | fixed, auto | auto |
duration.seconds | integer | No | 4–30, step 1 s; only for fixed duration | None |
output.aspect_ratio | string | No | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive | adaptive |
output.format | string | No | mp4 | mp4 |
output.resolution | string | No | 480p, 720p, 1080p | 720p |
prompt | string | Yes | string | None |
watermark | boolean | No | false, true | false |
Media requirements
| Media role | Type and count | Formats | Per-file limits |
|---|---|---|---|
reference_image | image, optional, at most 30 | jpeg, png, webp, bmp, tiff, gif, heic, heif | size 1–31457279 bytes; width 300–6000 px; height 300–6000 px |
reference_video | video, optional, at most 10 | mp4, mov | size at most 200 MB; width 300–6000 px; height 300–6000 px; duration 2–30 s; frame rate at least 24 fps, and at most 60 fps; total for this role at most 30 s |
reference_audio | audio, optional, at most 10 | wav, mp3 | size at most 15 MB; duration 2–30 s; total for this role at most 30 s |
Whether media is required also depends on the combination constraints below.
Combination constraints
duration.mode="fixed"requiresduration.seconds. Include the number of seconds whenever you explicitly setfixed.- Do not send
duration.secondswhen usingduration.mode="auto". - Provide at least one of these roles:
reference_image,reference_video,reference_audio.
Request example
Save the JSON below as request.json, then follow the shared workflow to quote first and create after confirmation.
{ "model": "doubao-seedance-2-5-260628", "operation": "reference_to_video", "prompt": "Create a product video of the blue ceramic mug in the reference image. Keep its shape and color.", "duration": { "mode": "fixed", "seconds": 5 }, "output": { "resolution": "720p", "aspect_ratio": "adaptive" }, "media": [ { "id": "reference", "type": "image", "role": "reference_image", "source": "https://docs.bettertoken.ai/images/nano-banana-guide/sample-07.png" } ]}Common 422 errors
| 422 error code | Action |
|---|---|
enum / range / step | Adjust values and increments to match this subsection’s field table. |
unsupported_field | Remove fields absent from this operation’s field table. |
requires | Add seconds, aspect ratio, audio settings or media as required by this subsection’s combination constraints. |
excludes | Remove fields that conflict with automatic duration or the last frame. |
count / media_role | Adjust roles and counts to match this subsection’s media table. |
video_input_unsupported | Check the public HTTPS URL, Content-Type and file format, then quote again. |
Official resources
When calling BetterToken, use this page’s fields and the corresponding operation in the live model catalog.

