2 models · video
Kandinsky API
Kandinsky is a family of AI video models made by Kandinsky Lab. varg runs 2 of them on one API key: Kandinsky 6.0 Pro and Kandinsky 6.0 Lite. Between them they cover text to video and image to video; they return video.
- Price
- From $0.08 per run Kandinsky 6.0 Lite
- Kandinsky 6.0 Pro
- From $0.24 per run
- Made by
- Kandinsky Lab
- Flagship id
kandinsky_6
Every Kandinsky 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.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kandinsky_6",
"prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
}'Kandinsky models and prices
Kandinsky on varg starts from $0.08 per run (Kandinsky 6.0 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.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
Kandinsky 6.0 Prokandinsky_ | Kandinsky 6.0 Pro by Kandinsky Lab. Open-weight text- and image-to-video with a synchronized audio track; 5-second clips, upscalable to 1080p or 4x. | Text to video, Image to video | From $0.24 per run$0.03/video | ~10 min |
Kandinsky 6.0 Litekandinsky_ | Kandinsky 6.0 Lite by Kandinsky Lab. Fast, low-cost open-weight text- and image-to-video with audio; 5-second clips, upscalable to 1080p or 4x. | Text to video, Image to video | From $0.08 per run$0.026/video | ~4 min |
Call the Kandinsky API
The call below runs Kandinsky 6.0 Pro. For another Kandinsky 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.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kandinsky_6",
"prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Kandinsky 6.0 Pro with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "video",
"input": {
"model": "kandinsky_6",
"prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
},
"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
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool video '{"model":"kandinsky_6","prompt":"A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."}'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 Kandinsky
Step-by-step pages on varg how to.
Kandinsky API: questions
- How much does the Kandinsky API cost on varg?
- The lowest price the catalog states in the Kandinsky family is from $0.08 per run ($0.026/video), on Kandinsky 6.0 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 Kandinsky models are on varg?
- 2: Kandinsky 6.0 Pro (from $0.24 per run) and Kandinsky 6.0 Lite (from $0.08 per run). Each has its own page with the parameters and a call to copy.
- Which Kandinsky models take an image?
- Both: Kandinsky 6.0 Pro and Kandinsky 6.0 Lite. The catalog lists image to video for them; pass the image as a URL in "files".
- Which Kandinsky models generate audio?
- Both: Kandinsky 6.0 Pro and Kandinsky 6.0 Lite. Set "audio": true in the request and the video comes with a native audio track.
- How long do Kandinsky requests take?
- Typically from about 4 min (Kandinsky 6.0 Lite) to about 10 min (Kandinsky 6.0 Pro), 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 Kandinsky 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": "kandinsky_6". 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 Kandinsky 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": "kandinsky_6".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/kandinsky_6.md (swap the id), and every model is listed in varg.ai/models/llms.txt.