Video

Generate video from text (Wan 2.5)

post

Generate video from text using Wan-AI/Wan2.5-T2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Wan text-to-video generation.

Uses Wan-AI/Wan2.5-T2V model for creating videos from text prompts.

promptstring · min: 1 · max: 2000Required

Text description of the video to generate

Example: A humanoid robot holding a flag that says 'RELAY', waving it proudly against a futuristic city skyline at sunset

modelany ofOptional

Video generation model. Available: 'Wan-AI/Wan2.5-T2V' (default)

Example: Wan-AI/Wan2.5-T2V

stringOptional

or

nullOptional

sizeany ofOptional

Video resolution: '832x480', '480x832', '1280x720', '720x1280'

Default: 832x480Example: 832x480

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds (5 or 10)

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

Example: blurry, low quality, distorted, watermark

string · max: 1000Optional

or

nullOptional

audio_urlany ofOptional

URL of audio file to include in the video

stringOptional

or

nullOptional

prompt_extendany ofOptional

Enable AI-powered prompt enhancement for better results

Default: false

booleanOptional

or

nullOptional

seedany ofOptional

Random seed for reproducible results

integer · max: 2147483647Optional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result. Default: false. Recommended: true for video (2-20 min runtime).

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/wan-25/t2v

HTTPcURLJavaScriptPython

POST /v2/video/wan-25/t2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 63

{
  "prompt": "A robot waving a flag against a futuristic skyline"
}

SimpleDetailed

{
  "videos": [
    "text"
  ],
  "model": "text",
  "size": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Image-to-video (Wan 2.5)

post

Generate video from image using Wan-AI/Wan2.5-I2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Wan image-to-video generation.

Uses Wan-AI/Wan2.5-I2V model to generate videos from a source image and text prompt.

promptstring · min: 1 · max: 2000Required

Text description to guide video generation

Example: A cat slowly turning its head toward the camera and blinking

first_frame_urlstringRequired

URL of the first frame image

Example: https://images.pexels.com/photos/2071873/pexels-photo-2071873.jpeg

resolutionany ofOptional

Video resolution: '480p', '720p', '1080p'

Default: 720pExample: 720p

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 5 or 10

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

Example: blurry, low quality, distorted, watermark

string · max: 1000Optional

or

nullOptional

audio_urlany ofOptional

URL of audio file to include in the video

stringOptional

or

nullOptional

enable_prompt_expansionany ofOptional

Enable AI-powered prompt enhancement for better results

Default: false

booleanOptional

or

nullOptional

seedany ofOptional

Random seed for reproducible results

integer · max: 2147483647Optional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result. Default: false. Recommended: true for video (2-20 min runtime).

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/wan-25/i2v

HTTPcURLJavaScriptPython

POST /v2/video/wan-25/i2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 122

{
  "prompt": "A cat turning its head",
  "first_frame_url": "https://images.pexels.com/photos/2071873/pexels-photo-2071873.jpeg"
}

SimpleDetailed

{
  "videos": [
    "text"
  ],
  "model": "Wan-AI/Wan2.5-I2V",
  "resolution": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Image-to-video (Sora 2)

post

Generate video from image using OpenAI Sora 2.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Sora image-to-video generation.

Uses OpenAI Sora 2 model for high-quality I2V generation.

first_frame_urlstringRequired

URL or base64 of the first frame image

Example: https://images.pexels.com/photos/2071873/pexels-photo-2071873.jpeg

promptany ofOptional

Optional text description to guide video generation

Example: The cat slowly turns and looks at the camera

string · max: 2000Optional

or

nullOptional

durationany ofOptional

Video duration in seconds: 4, 8, or 12

Default: 4

integer · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately, poll /v2/tasks/{task_address} for result. Default: false. Recommended: true for video (2-20 min runtime).

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/sora-2/i2v

HTTPcURLJavaScriptPython

POST /v2/video/sora-2/i2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 88

{
  "first_frame_url": "https://images.pexels.com/photos/2071873/pexels-photo-2071873.jpeg"
}

SimpleWith Prompt

{
  "videos": [
    "text"
  ],
  "model": "openai/sora-2-I2V",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Text-to-video (Sora 2)

post

Generate video from text using OpenAI Sora 2.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Sora text-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description of the video to generate

sizeany ofOptional

Video resolution (portrait or landscape)

Default: 720x1280

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 4, 8, or 12

Default: 4

integer · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/sora-2/t2v

HTTPcURLJavaScriptPython

POST /v2/video/sora-2/t2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 55

{
  "prompt": "A robot waving a flag in a futuristic city"
}

SimpleLandscape

{
  "videos": [
    "text"
  ],
  "model": "openai/sora-2-T2V",
  "size": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Text-to-video (Sora 2 Pro)

post

Generate video from text using OpenAI Sora 2 Pro (higher quality).

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Sora Pro text-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description of the video to generate

sizeany ofOptional

Video resolution

Default: 720x1280

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 4, 8, or 12

Default: 4

integer · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/sora-2-pro/t2v

HTTPcURLJavaScriptPython

POST /v2/video/sora-2-pro/t2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 63

{
  "prompt": "A cinematic shot of a dragon flying over mountains"
}

SimpleHigh Resolution

{
  "videos": [
    "text"
  ],
  "model": "openai/sora-2-pro-T2V",
  "size": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Image-to-video (Sora 2 Pro)

post

Generate video from image using OpenAI Sora 2 Pro (higher quality).

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Sora Pro image-to-video generation.

first_frame_urlstringRequired

URL or base64 of the first frame image

promptany ofOptional

Optional text description to guide generation

string · max: 2000Optional

or

nullOptional

resolutionany ofOptional

Video resolution

Default: 720p

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 4, 8, or 12

Default: 4

integer · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/sora-2-pro/i2v

HTTPcURLJavaScriptPython

POST /v2/video/sora-2-pro/i2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 88

{
  "first_frame_url": "https://images.pexels.com/photos/2071873/pexels-photo-2071873.jpeg"
}

SimpleWith Prompt

{
  "videos": [
    "text"
  ],
  "model": "openai/sora-2-pro-I2V",
  "resolution": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate video from text (Kling v2.6)

post

Generate video from text using KlingTeam/v2.6-T2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Kling text-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description of the video to generate

aspect_ratioany ofOptional

Video aspect ratio

Default: 16:9

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 5 or 10

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

string · max: 1000Optional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/kling-26/t2v

HTTPcURLJavaScriptPython

POST /v2/video/kling-26/t2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 39

{
  "prompt": "A car driving on a highway"
}

SimpleDetailed

{
  "urls": [
    "text"
  ],
  "model": "KlingTeam/v2.6-T2V",
  "aspect_ratio": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Image-to-video (Kling v2.6)

post

Generate video from image using KlingTeam/v2.6-I2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Kling image-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description to guide video generation

imagestringRequired

Reference image URL or base64 encoded string

image_tailany ofOptional

End frame image URL or base64 encoded string (optional)

stringOptional

or

nullOptional

aspect_ratioany ofOptional

Video aspect ratio

Default: 16:9

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 5 or 10

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

string · max: 1000Optional

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/kling-26/i2v

HTTPcURLJavaScriptPython

POST /v2/video/kling-26/i2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 86

{
  "prompt": "The scene comes alive",
  "image": "https://picsum.photos/id/10/1024/1024.jpg"
}

SimpleDetailed

{
  "urls": [
    "text"
  ],
  "model": "KlingTeam/v2.6-I2V",
  "aspect_ratio": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Generate video from text (Wan 2.6)

post

Generate video from text using Wan-AI/Wan2.6-T2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Wan 2.6 text-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description of the video to generate

sizeany ofOptional

Video resolution

Default: 1280x720

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 5, 10, or 15

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

string · max: 1000Optional

or

nullOptional

audio_urlany ofOptional

URL of audio file to include in the video

stringOptional

or

nullOptional

prompt_extendany ofOptional

Enable AI-powered prompt enhancement

Default: true

booleanOptional

or

nullOptional

seedany ofOptional

Random seed for reproducibility

integer · max: 2147483647Optional

or

nullOptional

shot_typeany ofOptional

Shot type: 'single' or 'multi'

string · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/wan-26/t2v

HTTPcURLJavaScriptPython

POST /v2/video/wan-26/t2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 39

{
  "prompt": "A dog running on the beach"
}

SimpleDetailed

{
  "urls": [
    "text"
  ],
  "model": "Wan-AI/Wan2.6-T2V",
  "size": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}

Image-to-video (Wan 2.6)

post

Generate video from image using Wan-AI/Wan2.6-I2V.

Header parameters

x-api-keyany ofOptional

stringOptional

or

nullOptional

Body

application/json

Request schema for Wan 2.6 image-to-video generation.

promptstring · min: 1 · max: 2000Required

Text description to guide video generation

first_frame_urlstringRequired

URL of the first frame image

resolutionany ofOptional

Video resolution: '720P' or '1080P'

Default: 1080P

string · enumOptionalPossible values:

or

nullOptional

durationany ofOptional

Video duration in seconds: 5, 10, or 15

Default: 5

integer · enumOptionalPossible values:

or

nullOptional

negative_promptany ofOptional

Things to avoid in the video

string · max: 1000Optional

or

nullOptional

audio_urlany ofOptional

URL of audio file to include in the video

stringOptional

or

nullOptional

prompt_extendany ofOptional

Enable AI-powered prompt enhancement

Default: true

booleanOptional

or

nullOptional

seedany ofOptional

Random seed for reproducibility

integer · max: 2147483647Optional

or

nullOptional

shot_typeany ofOptional

Shot type: 'single' or 'multi'

string · enumOptionalPossible values:

or

nullOptional

modeany ofOptional

Routing mode: 'auto' or 'direct' (video is direct-only)

Default: auto

string · enumOptionalPossible values:

or

nullOptional

asyncany ofOptional

Return task_address immediately for polling

Default: false

booleanOptional

or

nullOptional

Responses

200

Successful Response

application/json

202

Task accepted (async mode).

application/json

422

Validation Error

application/json

post

/v2/video/wan-26/i2v

HTTPcURLJavaScriptPython

POST /v2/video/wan-26/i2v HTTP/1.1
Content-Type: application/json
Accept: */*
Content-Length: 96

{
  "prompt": "The scene comes alive",
  "first_frame_url": "https://picsum.photos/id/10/1024/1024.jpg"
}

SimpleDetailed

{
  "urls": [
    "text"
  ],
  "model": "Wan-AI/Wan2.6-I2V",
  "resolution": "text",
  "duration": 1,
  "task_address": "text",
  "mode": "text",
  "done": true,
  "ANY_ADDITIONAL_PROPERTY": "anything"
}