Pixverse v6 Video Generation

curl --request POST \
  --url https://api.apimart.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "pixverse-v6",
    "prompt": "A cinematic shot of a corgi running through a sunflower field at golden hour",
    "size": "16:9",
    "resolution": "540p",
    "duration": 5
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JWXXXXXXXXXXXX"
    }
  ]
}

POST

videos

generations

curl --request POST \
  --url https://api.apimart.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "pixverse-v6",
    "prompt": "A cinematic shot of a corgi running through a sunflower field at golden hour",
    "size": "16:9",
    "resolution": "540p",
    "duration": 5
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JWXXXXXXXXXXXX"
    }
  ]
}

curl --request POST \
  --url https://api.apimart.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "pixverse-v6",
    "prompt": "A cinematic shot of a corgi running through a sunflower field at golden hour",
    "size": "16:9",
    "resolution": "540p",
    "duration": 5
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01JWXXXXXXXXXXXX"
    }
  ]
}

Authentication

Authorization

string

required

All endpoints require authentication using a Bearer Token.Get an API Key:Visit the API Key management page to obtain your API Key.Add the following header in your request:

Authorization: Bearer YOUR_API_KEY

Request Parameters

model

string

required

Video generation model name. Fixed to pixverse-v6.

prompt

string

required

Video content description, up to 5000 characters. Required for all modes.

resolution

string

default:"540p"

Video resolution tier; directly affects pricing.

360p: SD
540p: Standard (default)
720p: HD
1080p: Full HD

Other resolution values will return a parameter error.

duration

integer

default:"5"

Video duration in seconds, range 1-15.

First/last frame transition mode only supports 5 or 8 seconds.

size

string

default:"16:9"

Video aspect ratio. Only effective in text-to-video and multi-reference fusion modes.

16:9: Landscape widescreen (default)
4:3: Landscape 4:3
1:1: Square
3:4: Portrait 3:4
9:16: Portrait vertical
2:3: Portrait 2:3
3:2: Landscape 3:2
21:9: Cinematic widescreen

seed

integer

default:"0"

Random seed, range 0-2147483647. Same prompt and seed can reproduce similar results.

negative_prompt

string

Negative prompt used to exclude unwanted content, up to 2048 characters.

audio

boolean

default:"false"

Whether to generate an audio track.

true: Generate audio (increases pricing)
false: No audio (default)

watermark

boolean

default:"false"

Whether to add a watermark in the bottom-right corner of the video.

true: Add watermark
false: No watermark (default)

motion_mode

string

Motion mode.

normal: Standard mode (pixverse-v6 only supports this value)

fast only applies to legacy models and will be rejected by the upstream when used with pixverse-v6.

generate_multi_clip_switch

boolean

default:"false"

Whether to generate a multi-clip continuous video. Only supported in text-to-video and image-to-video modes.

true: Generate multi-clip continuous video
false: Single clip (default)

image_urls

array<url>

Input image URL array for image-to-video; only the first image is used.Images must be publicly accessible HTTP/HTTPS URLs.

first_frame_image

url

First frame image URL for transition mode. Must be provided together with last_frame_image.

last_frame_image

url

Last frame image URL for transition mode. Must be provided together with first_frame_image.

img_references

array<url>

Reference image URL array for multi-reference fusion mode; supports 1-7 images.Providing this field triggers multi-reference fusion mode.

extend_from_task_id

string

Source task ID for video extension. Providing this field triggers video extension mode.The source task must belong to the current user, use model pixverse-v6, and have status completed.

Generation Modes

The adapter automatically dispatches to the corresponding generation mode based on request fields. Matching is done in priority order; the first match wins.

Mode	Trigger	Description
Text-to-video	No image or extension fields	Generate video based on `prompt`
Image-to-video	`image_urls` with one image	Use the first image as input
First/last frame transition	Both `first_frame_image` and `last_frame_image` provided	Generate a smooth transition between two frames
Multi-reference fusion	`img_references` array provided	Fuse 1-7 reference images into a video
Video extension	`extend_from_task_id` provided	Continue generation from a completed Pixverse task

All image inputs only accept publicly accessible HTTP/HTTPS URLs. base64 and Data URI are not supported. If you only have local images, upload them to object storage first and pass the URL.

Parameter Rules

Constraint	Description
Duration	`1 ≤ duration ≤ 15` seconds; transition mode only supports `5` or `8` seconds
Resolution	Only `360p`, `540p`, `720p`, `1080p` are supported
Aspect ratio	`size` is only effective in text-to-video and multi-reference fusion modes
Prompt length	`prompt` up to 5000 chars, `negative_prompt` up to 2048 chars
Image-to-video	`image_urls` only uses the first image
Transition	`first_frame_image` and `last_frame_image` must be provided together
Motion mode	`pixverse-v6` only supports `normal`
Multi-reference fusion	`img_references` supports 1-7 images
Video extension	`extend_from_task_id` must point to a `completed` `pixverse-v6` task owned by the current user

Response

code

integer

Response status code. 200 on success.

data

array

Returned task array.

Show Array element

status

string

Initial task status. submitted upon successful submission.

task_id

string

Unique task identifier used for querying status and results.

Querying Task Results

Video generation is an asynchronous task. After submission, a task_id is returned. Use the Get Task Status endpoint to query progress and results.

cURL

curl --request GET \
  --url https://api.apimart.ai/v1/tasks/task_01JWXXXXXXXXXXXX \
  --header 'Authorization: Bearer <token>'

It is recommended to poll every 5 seconds until the status becomes completed or failed.

Successful Result Example

{
  "code": 200,
  "data": {
    "id": "task_01KSPX48B8V1M6C2ZN0D0T4BKB",
    "status": "completed",
    "progress": 100,
    "cost": 0.2,
    "created": 1779958948,
    "completed": 1779958999,
    "estimated_time": 100,
    "actual_time": 51,
    "result": {
      "videos": [
        {
          "url": ["https://upload.apimart.ai/f/video/xxxx.mp4"],
          "expires_at": 1780045399
        }
      ]
    }
  }
}

The video URL is at data.result.videos[0].url[0]. The url field is itself an array. Video links typically expire after 24 hours; download or transfer them in time.

Failed Result Example

{
  "code": 200,
  "data": {
    "id": "task_01KSPX48B8V1M6C2ZN0D0T4BKB",
    "status": "failed",
    "progress": 100,
    "cost": 0,
    "created": 1779958948,
    "completed": 1779958960,
    "error": {
      "code": "task_failed",
      "message": "pixverse error 400063: moderation failed",
      "type": "task_failed"
    }
  }
}

On failure, cost is typically 0. Read the error reason from data.error.message.

Use Cases

Case 1: Text-to-video

{
  "model": "pixverse-v6",
  "prompt": "A neon-lit alley in Tokyo at night, light rain, anamorphic lens flare",
  "size": "21:9",
  "resolution": "720p",
  "duration": 8,
  "seed": 42,
  "audio": true
}

Case 2: Image-to-video

{
  "model": "pixverse-v6",
  "prompt": "Camera slowly zooms in, gentle wind moves the leaves",
  "image_urls": ["https://example.com/first-frame.jpg"],
  "resolution": "540p",
  "duration": 5
}

Case 3: First/Last Frame Transition

{
  "model": "pixverse-v6",
  "prompt": "transform smoothly from a puppy to a cat",
  "first_frame_image": "https://example.com/puppy.jpg",
  "last_frame_image": "https://example.com/cat.jpg",
  "resolution": "540p",
  "duration": 5,
  "motion_mode": "normal"
}

Case 4: Multi-Reference Fusion

{
  "model": "pixverse-v6",
  "prompt": "A girl wearing the outfit from image 2, holding the cat from image 3",
  "img_references": [
    "https://example.com/character.jpg",
    "https://example.com/outfit.jpg",
    "https://example.com/cat.jpg"
  ],
  "size": "9:16",
  "resolution": "720p",
  "duration": 5
}

Case 5: Video Extension

{
  "model": "pixverse-v6",
  "prompt": "the character now walks into a forest",
  "extend_from_task_id": "task_01JWXXXXXXXXXXXX",
  "resolution": "540p",
  "duration": 5
}

Grok Imagine 1.0 Video Generation Omni-Flash-Ext Video Generation

Documentation Index

​Authentication

​Request Parameters

​Generation Modes

​Parameter Rules

​Response

​Querying Task Results

​Successful Result Example

​Failed Result Example

​Use Cases

​Case 1: Text-to-video

​Case 2: Image-to-video

​Case 3: First/Last Frame Transition

​Case 4: Multi-Reference Fusion

​Case 5: Video Extension

Authentication

Request Parameters

Generation Modes

Parameter Rules

Response

Querying Task Results

Successful Result Example

Failed Result Example

Use Cases

Case 1: Text-to-video

Case 2: Image-to-video

Case 3: First/Last Frame Transition

Case 4: Multi-Reference Fusion

Case 5: Video Extension