Grok Imagine Video Extend

xai/grok-imagine-video/video-extend

Grok Imagine Video Extend is xAI's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Use in agent Get API key

Base price: $0.36USD / run
Execution: async
Model type: video
Input fields: 3

Production route

Try the model

Playground

Open playground

Input

Prompt(string)

Text description of what should happen next in the video.

Video URL(string)

URL of the source video to extend. Must be MP4 format (H.264, H.265, or AV1 codec), 2-15 seconds long.

Duration(integer)

210

Length of the extension in seconds. Range: 2 to 10.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Model card

Specifications

Pricing

Base price: $0.36 / run

Context & modalities

Input: Schema-defined
Output: video

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: xAI
Model ID: xai/grok-imagine-video/video-extend
Execution: async
API: Unified Run API
Endpoint: /v1/run

API README

Grok Imagine Video Extend

Grok Imagine Video Extend is a specialized SandBase endpoint built to continue an existing clip beyond its current endpoint. It is most useful when teams need prompt-directed continuation that carries motion and scene logic into a new segment, with the route’s inputs defining a repeatable production contract instead of leaving critical delivery choices to an ad-hoc manual workflow.

Use this exact route when its input mode matches the creative asset already in hand: describe the visual or spoken result clearly, set only the controls that support the intended delivery, and keep the subject, action, environment, camera or performance direction internally consistent. The result is returned asynchronously as a downloadable media URL suitable for review, automation, or downstream finishing.

Highlights

Continuation beyond the cut. Generate what happens after an existing clip ends, using the source endpoint as the visual and temporal handoff.
Prompt-directed next action. Describe the following movement, camera behavior, or story beat so the extension has a specific purpose rather than generic motion.
Codec-friendly source handling. The route accepts MP4 sources encoded with H.264, H.265, or AV1 across the documented 2–15 second input window.
Adjustable added length. Request 2–10 seconds of new footage to bridge a transition, hold a scene, or complete an interrupted action.

Pricing

Pricing scales with extension duration. The configured formula uses $0.0600 per second at its standard tier and $0.0800 per second when the resolved tier is 720p.

Extension	Resolved tier	Price
2 sec	480p / Auto	$0.1200
2 sec	720p	$0.1600
3 sec	480p / Auto	$0.1800
3 sec	720p	$0.2400
4 sec	480p / Auto	$0.2400
4 sec	720p	$0.3200
5 sec	480p / Auto	$0.3000
5 sec	720p	$0.4000
6 sec	480p / Auto	$0.3600
6 sec	720p	$0.4800
7 sec	480p / Auto	$0.4200
7 sec	720p	$0.5600
8 sec	480p / Auto	$0.4800
8 sec	720p	$0.6400
9 sec	480p / Auto	$0.5400
9 sec	720p	$0.7200
10 sec	480p / Auto	$0.6000
10 sec	720p	$0.8000

When to Use

Scenario	Why this route fits
Concept development	Choose Grok Imagine Video Extend when its extend workflow matches the starting material and you need several clearly directed variations.
Production iteration	Use explicit duration, resolution, ratio, seed, or quality controls to compare versions without changing the core creative brief.
Channel adaptation	Generate directly in the landscape, square, portrait, or vertical format required by the destination whenever that control is available.
Automated pipelines	Integrate the asynchronous media URL into review queues, asset libraries, publishing tools, or a later finishing stage.
Alternative route	Pick a related text-, image-, reference-, edit-, or turbo route when the available source media or required degree of control is different.

Prompt Guide

Lead with the main subject or source asset, then describe the intended action or transformation, environment, composition, camera or vocal delivery, lighting and mood. Keep instructions concrete and compatible; use the route’s explicit fields for duration, resolution, ratio, quality, voice, or reproducibility instead of burying those settings in prose.

{
  "prompt": "A cinematic product reveal with deliberate subject motion, coherent lighting, and a slow camera push.",
  "duration": 6,
  "video": "https://example.com/input.mp4"
}

Technical Specs

Property	Details
Model ID	`xai/grok-imagine-video/video-extend`
Required inputs	`prompt`
Execution	Asynchronous; poll the returned generation ID
Output	Downloadable media URL
`video`	string; optional
`prompt`	string; required
`duration`	integer; optional; range: 2–10; default: 6

Related Models

Model	Best for
`xai/grok-tts`	Alternative grok tts workflow
`xai/grok-imagine-video/text-to-video`	Alternative text to video workflow
`xai/grok-imagine-video/image-to-video`	Alternative image to video workflow
`xai/grok-imagine-video/reference-to-video`	Alternative reference to video workflow

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

xai/grok-imagine-video/video-extend

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "xai/grok-imagine-video/video-extend",
  "video": "https://static.sandbase.ai/examples/xai/grok-imagine-video/extend/input_video_0.mp4",
  "prompt": "The camera slowly zooms out to reveal the city skyline at sunset",
  "duration": 6
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
Grok Imagine Video ExtendThis model `xAI`	Video	$0.36 / run	Mar 24, 2026
Grok Imagine Video 1.5 Reference to Video `xAI`	Video	$1.13 / run	Aug 1, 2026
Grok Imagine Video 1.5 Text to Video `xAI`	Video	$0.84 / run	Aug 1, 2026
Grok Imagine Video 1.5 Image to Video `xAI`	Video	$0.85 / run	May 31, 2026
Grok Imagine Video Reference to Video `xAI`	Video	$0.56 / run	Mar 24, 2026
Grok Imagine Video Edit `xAI`	Video	$0.30 / run	Jan 29, 2026

Questions

FAQ

How do I call xAI Grok Imagine Video Extend through SandBase?

Create a SandBase API key, then send requests with the model ID "xai/grok-imagine-video/video-extend" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate xAI account?

No. One SandBase API key and balance gives you access to xAI Grok Imagine Video Extend and the other models in the catalog; you do not need to sign up with xAI separately.