Grok Imagine video API: price per second, request and code

What a Grok Imagine clip costs

Credits per clip from text, by resolution and length (6 seconds). Dollars are at the headline credit price; plans with more credits pay less per credit.

Computed from the quote the API charges with, as of 15 Nov 2026. The shortest, cheapest run is 55 credits; the longest at 720p is 80.

One request, then wait for the job

Video takes one to several minutes, so POST /api/v1/videos charges the run and answers at once with a job in queued. Read GET /api/v1/jobs/{id}?wait=50: it holds the line for up to 50 seconds and returns early the moment the job is final. The body below is the cheapest valid Grok Imagine request, 6 seconds at 480p, which costs 55 credits.

curl -X POST https://kinoseed.app/api/v1/videos \
  -H "Authorization: Bearer ks_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a lighthouse at dusk, waves breaking, slow aerial orbit",
    "model": "grok-imagine-video",
    "duration": 6,
    "aspect": "16:9",
    "resolution": "480p"
  }'

Send the same body to Quote first if you want the number before you spend anything; it charges nothing. Fields and errors are on Videos and Jobs.

The same run from an agent over MCP

An agent connected to the MCP server sends the same arguments to the generate_video tool. It returns the job at once, and the agent follows it with get_job until the status is completed or failed. Results are URLs, never inline video, so a clip does not fill the context window. Setup for Claude Code, Cursor and others is in the MCP server for video generation guide.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate_video",
    "arguments": {
      "prompt": "a lighthouse at dusk, waves breaking, slow aerial orbit",
      "model": "grok-imagine-video",
      "duration": 6,
      "aspect": "16:9",
      "resolution": "480p"
    }
  }
}

What Grok Imagine accepts

Every field is optional except prompt and model; anything outside the model's range is snapped to the nearest value it allows, and the quote follows the snapped value.

• duration: 6 seconds.
• aspect: 16:9, 9:16 or 1:1.
• resolution: 480p or 720p.
• startImageUrl: a first frame to animate. It does not change the price.
• endImageUrl: not taken by this model.
• Sound: Sound comes with every clip and is part of the price (per fal's model page as of 13 Nov 2026), so there is no audio switch.

Input images must be public https URLs or URLs returned by POST /files. The API refuses private addresses, localhost and plain http before anything fetches them.

What moves the price

Resolution and length. At 6 seconds, Grok Imagine is 55 credits at 480p and 80 at 720p. Doubling the length roughly doubles the price, since the provider bills per second of output.

For drafts, a cheaper model often does the job: a 5 second Wan 3.0 clip at 480p is 50 credits. Test the prompt there, then run the keeper on Grok Imagine. Every model's rate per second is side by side in AI video API price per second.

When to pick Grok Imagine

Pick Grok Imagine for short clips that come with sound (per fal's model page as of 13 Nov 2026) at a low price per run: a 6 second social clip, a reaction, an ambient scene. It works from text or from a start frame, at 480p or 720p.

It makes one length only, so for longer shots or a set last frame use Seedance 2.5 or MiniMax H3. Studio users get it in the Video studio; the Grok Imagine model page has its prices and specs, and how to use Grok Imagine covers prompts.

Failures, retries and limits

A run that fails is refunded automatically, and the job says so, so a provider error never costs credits. Identical requests sent close together return the same job instead of charging twice, and an Idempotency-Key header makes that explicit for retries from your own code.

An account runs up to 5 generations at once; a sixth request gets a 429 too_many_running error with a Retry-After header, before anything is charged. Results carry no watermark. Rate limits and error codes are on Errors and Rate limits.