7 models · video and image

Grok Imagine API

Grok Imagine is a family of AI video and image models made by xAI. varg runs 7 of them on one API key: Grok Imagine 1.5, Grok Imagine Image 2.0, Grok Imagine Video and 4 more. Between them they cover text to video, image to video, text to image, image to image and video edit; they return video and images.

Price
From $0.02 per run Grok Imagine 1.5 Lite
Grok Imagine 1.5
From $0.08 per run
Made by
xAI
Flagship id
grok_imagine_1_5

Every Grok Imagine model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.

POST /v2/tools/video/call
curl -X POST https://api.varg.ai/v2/tools/video/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok_imagine_1_5",
  "prompt": "A neon koi fish swims through a flooded Tokyo alley at night, rain hissing on the water.",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 6
}'
Try Grok Imagine 1.5 in the PlaygroundGet an API key

Grok Imagine models and prices

Grok Imagine on varg starts from $0.02 per run (Grok Imagine 1.5 Lite). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.

Grok Imagine models on varg
ModelCatalog descriptionTakesPriceTypical time
Grok Imagine 1.5grok_imagine_1_5Grok Imagine Video 1.5 by xAI. Text, image and multi-reference video with native audio, 1-15 seconds up to 1080p.Text to video, Image to videoFrom $0.08 per runfrom $0.08/s~60 s
Grok Imagine Image 2.0grok_imagine_image_2Grok Imagine Image 2.0 by xAI. Top-ranked image generation and editing with strong text rendering, up to 2K.Text to image, Image to imageFrom $0.04 per runfrom $0.04/image~20 s
Grok Imagine Videogrok_imaginexAI Grok video generation. Text-to-video and image-to-video.Text to video, Image to videoFrom $1.00 per run~2 min
Grok Imagine 1.5 Litegrok_imagine_1_5_liteGrok Imagine Video 1.5 Lite by xAI. The cheapest video with native audio: text or image to video, 1-15 seconds up to 1080p.Text to video, Image to videoFrom $0.02 per runfrom $0.02/s~40 s
Grok Imagine Video Editgrok_imagine_editxAI Grok video editing. Transform existing videos with text prompts.Video editFrom $1.00 per run~2 min
Grok Imagine Imagegrok_imagine_imagexAI Grok image generation.Text to imageFrom $0.03 per run$0.03/image~15 s
Grok Imagine Image Editgrok_imagine_image/editxAI Grok image editing.Image to imageFrom $0.03 per run$0.03/image~15 s

Call the Grok Imagine API

The call below runs Grok Imagine 1.5. For another Grok Imagine model, put its id from the table in "model"; the rest of the request keeps its shape.

REST

POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.

POST /v2/tools/video/call
curl -X POST https://api.varg.ai/v2/tools/video/call \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "grok_imagine_1_5",
  "prompt": "A neon koi fish swims through a flooded Tokyo alley at night, rain hissing on the water.",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 6
}'

From Claude, ChatGPT or Cursor (MCP)

The varg MCP server, https://mcp.varg.ai/mcp, runs Grok Imagine 1.5 with call_tool. Sign in with varg, no API key to paste. How to connect it

Claude Code
claude mcp add --transport http varg https://mcp.varg.ai/mcp
call_tool
{
  "tool": "video",
  "input": {
    "model": "grok_imagine_1_5",
    "prompt": "A neon koi fish swims through a flooded Tokyo alley at night, rain hissing on the water.",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 6
  },
  "wait": true
}

From a terminal (CLI)

vargai is the varg command line: every tool of the MCP server is a command. Install and log in

vargai
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool video '{"model":"grok_imagine_1_5","prompt":"A neon koi fish swims through a flooded Tokyo alley at night, rain hissing on the water.","aspect_ratio":"16:9","resolution":"720p","duration":6}'

How billing works

Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing

How to use Grok Imagine

Step-by-step pages on varg how to.

Grok Imagine API: questions

How much does the Grok Imagine API cost on varg?
The lowest price the catalog states in the Grok Imagine family is from $0.02 per run (from $0.02/s), on Grok Imagine 1.5 Lite. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
Which Grok Imagine models are on varg?
7: Grok Imagine 1.5 (from $0.08 per run), Grok Imagine Image 2.0 (from $0.04 per run), Grok Imagine Video (from $1.00 per run), Grok Imagine 1.5 Lite (from $0.02 per run), Grok Imagine Video Edit (from $1.00 per run), Grok Imagine Image (from $0.03 per run) and Grok Imagine Image Edit (from $0.03 per run). Each has its own page with the parameters and a call to copy.
Which Grok Imagine models take an image?
5 of the 7: Grok Imagine 1.5, Grok Imagine Image 2.0, Grok Imagine Video, Grok Imagine 1.5 Lite and Grok Imagine Image Edit. The catalog lists image to video and image to image for them; pass the image as a URL in "files".
What is the longest clip the Grok Imagine models make?
15 seconds, on Grok Imagine 1.5, Grok Imagine Video and Grok Imagine 1.5 Lite, by the models' input schemas.
How long do Grok Imagine requests take?
Typically from about 15 s (Grok Imagine Image) to about 2 min (Grok Imagine Video), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
How do I call the Grok Imagine API?
Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "grok_imagine_1_5". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
Can I use Grok Imagine from Claude, ChatGPT or Cursor?
Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "video" and the model id, for example "model": "grok_imagine_1_5".

More model APIs

Same API key, same request shape: change the model string to switch.

All models

For AI agents: each model above has its full spec as Markdown at varg.ai/models/grok_imagine_1_5.md (swap the id), and every model is listed in varg.ai/models/llms.txt.