video

A command-line tool for creating videos with Grok Imagine from a text description, an image, or reference images. It can turn a still image into an animated video or generate a video from words alone.

In plain words
What is it for?
Generating text-to-video clips, animating local or online images, creating product reveals from reference images, setting a duration, and returning results as JSON.
Why use it?
It lets scripts create or animate video content without manually building the whole scene in a video editor.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/moore-developers/grok-cli/video
Clone the repo
git clone --depth 1 https://github.com/Moore-developers/grok-cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00771
Opus 5 $0.00000 $0.00385
Sonnet 5 $0.00000 $0.00154
Haiku 4.5 $0.00000 $0.00077

Measured 2d ago against content hash 5c84165dc3dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/commands/video.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grok-cli video

Purpose

Generate video with Grok Imagine, including text-to-video, image-to-video, and reference-image video.

Common Usage

Text-to-video:

grok-cli video "Animate a futuristic skyline" --duration 8

Image-to-video from a URL:

grok-cli video "Make the scene slowly move" --image-url "https://example.com/source.png"

Image-to-video from a local file:

grok-cli video "Make the scene slowly move" --image ./source.png

Reference-image video from a URL:

grok-cli video "Create a product reveal" --reference-image-url "https://example.com/ref-1.png"

Reference-image video from local files:

grok-cli video "Create a product reveal" --reference-image ./ref-1.png --reference-image ./ref-2.png

Script or skill usage:

grok-cli video --json --prompt "Animate a futuristic skyline" --duration 8

Parameters

  • PROMPT: positional video prompt.
  • --prompt <PROMPT>: explicit script-friendly prompt.
  • --json: use the standard JSON envelope.
  • --auth-file <PATH>: override the OAuth state file path.
  • --image-url <URL>: source image URL for image-to-video.
  • --image <PATH>: local source image path for image-to-video.
  • --reference-image-url <URL>: repeatable reference image URL, up to 7.
  • --reference-image <PATH>: repeatable local reference image path, up to 7.
  • --duration <SECONDS>: video duration, normalized by the command.
  • --aspect-ratio <RATIO>: aspect ratio, supports 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.
  • --resolution <VALUE>: resolution, supports 480p and 720p.
  • --model <MODEL>: override the model for this video request only.
  • --timeout <SECONDS>: total polling timeout, default 600; individual create / poll requests still use a 120 second ceiling.

Behavior

  • Default model is grok-imagine-video.
  • grok-cli model does not manage the video default model; pass --model directly when needed.
  • Only one input mode is allowed: --image-url, --image, --reference-image-url, or --reference-image.
  • --reference-image-url and --reference-image together accept up to 7 items.
  • Local images are encoded as data URIs before being sent as image.url or reference_images[].url.
  • Default duration is 8 seconds. Normal videos max out at 15 seconds. Reference-image videos max out at 10 seconds.
  • Default aspect ratio is 16:9 and default resolution is 720p.
  • The command first calls POST /videos/generations, then polls GET /videos/{request_id}.
  • Access token expiry is checked before requests and polling. If needed, the command refreshes first.
  • Successful calls are written to the local usage SQLite database under video usage.

Read the full file on GitHub · 91 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 91 lines · 0 tokens per session scan A 5c84165dc3dc

Subscribe to this mod's changes

video is a command published in the GitHub repository Moore-developers/grok-cli (52 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 771 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.