Grok Imagine Video 1.5 API: Image-to-Video Animation

Overview

Grok Imagine Video 1.5 creates short videos from reference images, first and last frames, timed middle keyframes, or a loop image. Use a text prompt to guide motion, camera movement, and scene changes.

Capability	Value
Model ID	`grok-imagine-video-1-5`
Mode	`image-to-video`
Prompt length	1-5000 characters
Reference images	Optional; up to 7 at `480p` or `720p`, up to 1 at `1080p`
Frame controls	Optional first frame, last frame, loop image, and up to 4 timed middle keyframes
Duration	Integer or integer string from `1` through `15` seconds
Resolutions	`480p`, `720p`, `1080p`; use a single first frame for `1080p` and prefer `720p` for combined frame controls
Aspect ratios	`auto`, `1:1`, `16:9`, `9:16`, `3:2`, `2:3`
Output	MP4 video URL array in `resultJson.resultUrls`

Choose the Grok video endpoint

APIXO endpoint	Modes	Duration	Direct image inputs
Grok Imagine Video	Text-to-video and image-to-video	6-30 whole seconds	1-7 at `480p` or `720p`; 1 at `1080p`
Grok Imagine Video 1.5	Image-to-video only	1-15 whole seconds	Up to 7 at `480p` or `720p`; 1 at `1080p`; dedicated frame controls are also available

These endpoints generate new clips; neither exposes video-input editing or native video extension. Grok Imagine Video 1.5 supports dedicated first/last frames, timed keyframes, and loop images as described below. Multiple image_urls entries remain reference images, not a first/last-frame pair. xAI’s native Extend feature is a separate API capability; do not send its parameters to these APIXO endpoints. For a longer sequence assembled from separate clips, see the Grok longer-video workflow. It explains clip planning and editing, and distinguishes this workflow from native video extension.

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/grok-imagine-video-1-5`	Submit a video generation task
`GET`	`/statusTask/grok-imagine-video-1-5?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits an image-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/grok-imagine-video-1-5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "prompt": "turn this product photo into a smooth rotating studio shot",
      "image_urls": [
        "https://example.com/product.png"
      ],
      "resolution": "480p",
      "duration": 5
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/grok-imagine-video-1-5?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "make this portrait move with a subtle cinematic camera push",
    "image_urls": [
      "https://example.com/ref.jpg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": "8"
  }
}

The mode field is optional on this endpoint. If omitted, APIXO uses image-to-video.

First, last, and timed middle frames

{
  "request_type": "async",
  "input": {
    "prompt": "The character raises a hand, then turns around and sits down.",
    "first_frame_url": "https://example.com/start.jpg",
    "last_frame_url": "https://example.com/end.jpg",
    "keyframes": [
      { "url": "https://example.com/raise-hand.jpg", "timestamp_s": 2.5 },
      { "url": "https://example.com/turn-around.jpg", "timestamp_s": 5 }
    ],
    "resolution": "720p",
    "duration": 8
  }
}

Loop video

{
  "input": {
    "prompt": "Gentle continuous motion, returning smoothly to the opening pose.",
    "loop_url": "https://example.com/loop.jpg",
    "resolution": "720p",
    "duration": 8
  }
}

1080p single first frame

{
  "input": {
    "prompt": "A gentle camera push toward the landscape.",
    "first_frame_url": "https://example.com/landscape.jpg",
    "resolution": "1080p",
    "duration": 5
  }
}

For 1080p, use a single first-frame image. Combining first and last frames with timed middle keyframes is currently unavailable at 1080p; prefer 720p for combined frame controls. The one-reference-image limit does not mean that every frame-control combination supports 1080p. Task acceptance is not generation success: poll until state is success or failed and read failMsg if generation fails.

Parameters

string

default:"async"

Result delivery mode. Omit this field or use async for polling with statusTask, or use callback for webhook delivery.

string

Required when request_type is callback. Must be a public HTTPS URL that can receive the final task payload. See Webhooks.

object

required

Grok Imagine Video 1.5 input parameters. Provide at least one image input through a non-empty image_urls array, first_frame_url, last_frame_url, loop_url, or a non-empty keyframes array. Use a single first frame at 1080p; prefer 720p for combined frame controls.

Show properties

string

default:"image-to-video"

Optional generation mode. This endpoint supports image-to-video only.

string

required

Text prompt describing the desired motion, camera movement, and scene changes. Supports 1-5000 characters. Empty prompts are rejected.

string[]

Optional public HTTP(S) reference image URLs: up to 7 at 480p or 720p, and up to 1 at 1080p. These are reference images, not an ordered first/last-frame pair. May be omitted or empty when another image input is provided. Empty strings and non-string array items are rejected. The count applies only to this array, not to first/last frames or keyframes.

string

Optional non-empty public HTTP(S) first-frame image URL. May be used alone or with reference images, a last frame, and timed keyframes at supported resolutions. Ignored when loop_url is provided, even if its value would otherwise be invalid. For 1080p, use a single first-frame image.

string

Optional non-empty public HTTP(S) last-frame image URL. May be used alone or with other image inputs at supported resolutions. Ignored when loop_url is provided, even if its value would otherwise be invalid. Prefer 720p for combined frame controls.

string

Optional non-empty public HTTP(S) image URL used for both the opening and closing frames. Takes precedence over first_frame_url and last_frame_url: both fields are ignored when loop_url is provided. Reference images and timed keyframes can still be included. Prefer 720p for loop workflows.

object[]

Optional array of up to 4 timed middle frames. Each object requires url, a non-empty public HTTP(S) image URL, and timestamp_s, a finite JSON number in seconds. Decimal times are supported; numeric strings are not. Each time must be greater than 0 and less than duration; any two times must be at least 1/3 second apart. The specified times are preserved, not automatically assigned. May be used alone or with other image inputs at supported resolutions. Prefer 720p for combined frame controls.

string

required

Output resolution tier. Supported values: 480p, 720p, 1080p. Values are case-insensitive. For 1080p, use a single first-frame image; combining first and last frames with timed middle keyframes is currently unavailable. Prefer 720p for combined frame controls. Poll the final task state to determine generation success.

integer|string

required

Output duration in seconds. Accepts a JSON integer or integer string from 1 through 15. Decimal values and negative values are not valid.

string

default:"auto"

Output aspect ratio. Supported values: auto, 1:1, 16:9, 9:16, 3:2, 2:3.

Use public, directly accessible image URLs. Choose clear source images with the subject visible and little obstruction for more predictable motion.

Response format

Submit task response

POST /generateTask/grok-imagine-video-1-5 returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: processing, success, or failed.

string

JSON string containing generated video URLs in resultUrls. Present when state is success.

string

Machine-readable failure code. Present when state is failed.

string

Human-readable failure message. Present when state is failed.

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds when available.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/grok-imagine-video-1-5" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "prompt": "make this character smile and look toward the camera",
      "image_urls": [
        "https://example.com/character.jpg"
      ],
      "resolution": "720p",
      "duration": 10
    }
  }'

The callback payload uses the same top-level shape as status polling with code, message, and data. Successful callbacks include the final state and resultJson. See Webhooks for delivery requirements and retry behavior.

Billing

New non-LLM requests use 1 credit = $0.001. Calculate the full amount, including billable quantity and add-ons, apply the applicable account discount, then round the request total upward to the next whole credit. Agreed fixed unit prices retain their precision and replace the standard price and discount; final rounding still applies. See credit conversion and rounding. Grok Imagine Video 1.5 is billed per second. The selected resolution determines the per-second unit price, and the submitted duration determines the billable seconds.

Resolution	APIXO price	Minimum valid request cost	Market display reference
`480p`	`$0.024 / second`	`$0.024` for 1 second	`$0.080 / second`
`720p`	`$0.045 / second`	`$0.045` for 1 second	`$0.140 / second`
`1080p`	`$0.080 / second`	`$0.080` for 1 second	`$0.200 / second`

Market display references are comparison values, not the charged amount. A 10-second request costs $0.240 at 480p, $0.450 at 720p, or $0.800 at 1080p before account discounts. Formula:

total cost = duration * resolution unit price

Reference image count, first and last frames, timed keyframes, and loop images do not add charges. Requests with the same resolution and duration use the same pricing. These are USD API usage charges. Studio monthly credits do not apply to API calls. For current API rates in USD, see API pricing.

Latency and polling

Grok Imagine Video 1.5 tasks are asynchronous. Actual latency may vary by prompt complexity, image accessibility, duration, resolution, and generation queue load.

Workload	Typical generation time	Recommended first poll	Poll interval
Image-to-video, 1-15 seconds	Varies by prompt, image count, resolution, and duration	30s after task creation	5s

For production workloads, use callback mode to avoid frequent polling while video tasks run.

Result URLs are temporary. Download and store important outputs promptly after task completion. Rate limits and concurrency can vary by account and API key. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing `input`, unsupported `mode`, missing `prompt`, no image input, invalid `resolution`, invalid `duration`, or invalid frame parameters	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`404`	Task not found when polling	Check the `taskId`
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unknown task failure	Retry with backoff
`502`	Service error	Retry with backoff
`504`	Service timeout	Retry later or use callback mode for long-running jobs

Validation notes

Condition	Backend behavior
Missing `input`	Request fails before task creation.
Missing `mode`	APIXO uses `image-to-video`.
Unsupported `mode`	Request fails before task creation. This endpoint only supports `image-to-video`.
Missing `prompt`	Request fails before task creation.
Empty `prompt` or more than 5000 characters	Request fails before task creation.
No non-empty image input in `image_urls`, `first_frame_url`, `last_frame_url`, `loop_url`, or `keyframes`	Request fails before task creation.
`image_urls` is not an array, contains empty strings, or contains non-string items	Request fails before task creation.
More than 7 `image_urls` at `480p` / `720p`, or more than 1 at `1080p`	Request fails before task creation.
`loop_url` provided together with `first_frame_url` or `last_frame_url`	The first/last-frame fields are ignored; reference images and keyframes remain usable.
More than 4 keyframes, missing keyframe fields, invalid times, or times less than 1/3 second apart	Request fails before task creation.
`1080p` with first/last frames and timed middle keyframes	Currently unavailable. Use `720p`; an accepted task can still finish with `state=failed`.
Missing `resolution`	Request fails before task creation.
Unsupported `resolution`	Request fails before task creation. Supported values are `480p`, `720p`, and `1080p`.
Missing `duration`	Request fails before task creation.
`duration` outside `1` through `15`, decimal, or negative	Request fails before task creation.
Missing `aspect_ratio`	Defaults to `auto`.
Unsupported `aspect_ratio`	Request fails before task creation. Use `auto`, `1:1`, `16:9`, `9:16`, `3:2`, or `2:3`.

Task failure codes

failCode identifies the task failure. Common values include:

Fail code	Meaning	What to do
`SensitiveContent`	Prompt or input/output content was rejected by safety checks	Change the prompt or reference image
`PromptInvalid`	Prompt was invalid or rejected	Rewrite the prompt and retry
`ImageFormatIncorrect`	Reference image format could not be processed	Use a public, direct image URL in a common image format
`RateLimited`	A rate limit was reached	Retry with exponential backoff
`Timeout`	The task timed out	Retry later or use callback mode
`Unknown error`	An unknown task failure occurred	Retry with backoff or contact support with the `taskId`

See Error Codes for the full error reference.

MCP integration

The complete model schema declares result decoding in mcp.result and supported file bindings in mcp.attachments. These are client integration metadata, not generation input parameters. Attachment paths: image_urls, first_frame_url, last_frame_url, loop_url, keyframes[].url. Preserve the user’s file order. For a path containing [], supply the parent array items and their metadata in input, then bind files to an explicit item index, such as [0]. Model parameter validation remains on the API.

​Overview

​Choose the Grok video endpoint

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Image-to-video

​First, last, and timed middle frames

​Loop video

​1080p single first frame

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Validation notes

​Task failure codes

​MCP integration

​Related links

Overview

Choose the Grok video endpoint

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Image-to-video

First, last, and timed middle frames

Loop video

1080p single first frame

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Validation notes

Task failure codes

MCP integration

Related links