How much does Kandinsky 6.0 Lite cost on varg?

Kandinsky 6.0 Lite costs from $0.08 per run on varg ($0.026/video on the cheapest route). varg charges the provider's price with no markup, from one credit balance. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.

How do I call the Kandinsky 6.0 Lite 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": "kandinsky_6_lite". 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 6.0 Lite 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 Kandinsky 6.0 Lite with call_tool, passing tool "video" and "model": "kandinsky_6_lite".

How long does a Kandinsky 6.0 Lite request take?

Typically about 4 min on the fastest route, by the catalog's estimate. The API answers at once with a job id, so nothing waits on an open connection while it runs.

Video · Text to video · Image to video

Kandinsky 6.0 Lite API

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.

Price: From $0.08 per run $0.026/video
Typical time: ~4 min
Model id: kandinsky_6_lite

Kandinsky 6.0 Lite 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": "kandinsky_6_lite",
  "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
}'

Try it in the Playground Get an API key

Kandinsky 6.0 Lite pricing

From $0.08 per run. Prices are in US dollars and are the provider's own, with no markup. Kandinsky 6.0 Lite has 2 routes: "model": "kandinsky_6_lite" picks one automatically, or pass a route key as "model" to pin it. For the exact price of a request, send the same body to POST https://api.varg.ai/v2/estimate.

fal $0.026/video
fal:fal-ai/kandinsky6-lite/text-to-video
Text to video Kandinsky 6.0 Lite text-to-video: fast, low-cost 5 s clips with audio.
Per video
$0.026
Extra per num_inference_steps
+$0.0134
Extra when upscale_factor is 2
+$0.16
Extra when upscale_factor is 2.25
+$0.16
Extra when upscale_factor is 4
+$0.49
Minimum charge
$0.08
Most one request can cost
$0.74
Typical time
~4 min
fal $0.026/video
fal:fal-ai/kandinsky6-lite/image-to-video
Image to video Kandinsky 6.0 Lite image-to-video: fast, low-cost 5 s clips from a first frame.
Per video
$0.026
Extra per num_inference_steps
+$0.0134
Extra when upscale_factor is 2
+$0.16
Extra when upscale_factor is 2.25
+$0.16
Extra when upscale_factor is 4
+$0.49
Minimum charge
$0.08
Most one request can cost
$0.74
Typical time
~4 min

Kandinsky 6.0 Lite inputs

The JSON body of the request. Media inputs are URLs: upload a local file with POST /v2/files and pass the URL it returns. Full JSON Schema, no key needed: api.varg.ai/v2/tools/video?model=kandinsky_6_lite

Kandinsky 6.0 Lite request fields
Field	What it does
`model` string required	`kandinsky_6_lite` picks a route automatically. To pin one, pass a route key from Pricing above.
`prompt` string	—
`files` array of { url }	—
`aspect_ratio` string	Allowed e.g. 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4 \| 21:9 \| auto
`resolution` string	Quality tier. Supported by this model: 480p, 1080p, 4k. Unsupported tiers fall back to the nearest available. Allowed 480p \| 720p \| 1080p \| 4k
`audio` boolean	Set true to generate the video with a native audio track.
`duration` integer	Length in seconds. Not mapped by this model — ignored if sent. Allowed 1–120

Provider options

Optional, under provider_options.<provider>. Only the options of the provider that runs the job apply; pin a route to choose it.

`provider_options.fal`

Kandinsky 6.0 Lite options for fal
Field	What it does
`prompt` string	The text prompt describing the video and its sound.
`sync_mode` boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
`aspect_ratio` string	Allowed 16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4
`generate_audio` boolean	Whether to generate a synchronized audio track.
`upscale_factor` number	—
`num_inference_steps` integer	The number of denoising steps. Lite is tuned for 10. Allowed 4–16
`enable_safety_checker` boolean	Authorized callers may set false to request relaxed screening.
`enable_prompt_expansion` boolean	Whether to rewrite the prompt into a detailed video+audio description with the model's own Qwen2.5-VL text encoder before generating.
`image_url` string (URL)	The image used as the first frame of the video.

Call the Kandinsky 6.0 Lite API

POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away.

1. Send the request

cURL

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_lite",
  "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
}'

JavaScript

const headers = {
  Authorization: `Bearer ${process.env.VARG_API_KEY}`,
  'Content-Type': 'application/json',
}

const res = await fetch('https://api.varg.ai/v2/tools/video/call', {
  method: 'POST',
  headers,
  body: JSON.stringify({
    "model": "kandinsky_6_lite",
    "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
  }),
})
const job = await res.json() // { id: "job_…", status: "queued" }

Python

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['VARG_API_KEY']}"}

job = requests.post(
    "https://api.varg.ai/v2/tools/video/call",
    headers=headers,
    json={
      "model": "kandinsky_6_lite",
      "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
    },
).json()  # {"id": "job_…", "status": "queued"}

2. Get the result

Poll the job until its status is completed, failed or cancelled; Kandinsky 6.0 Lite typically takes about 4 min. The result is at output.outputs[0].url.

GET /v2/jobs/{id}

curl https://api.varg.ai/v2/jobs/$JOB_ID \
  -H "Authorization: Bearer $VARG_API_KEY"

# Poll until "status" is completed, failed or cancelled.
# The result is in output.outputs[0].url

JavaScript

let current = job
while (!['completed', 'failed', 'cancelled'].includes(current.status)) {
  await new Promise((resolve) => setTimeout(resolve, 3000))
  current = await (await fetch(`https://api.varg.ai/v2/jobs/${current.id}`, { headers })).json()
}
console.log(current.output?.outputs?.[0]?.url)

Python

import time

while job["status"] not in ("completed", "failed", "cancelled"):
    time.sleep(3)
    job = requests.get(f"https://api.varg.ai/v2/jobs/{job['id']}", headers=headers).json()

print(job["output"]["outputs"][0]["url"])

Or take a webhook instead of polling

Add options.webhook_url and varg POSTs the finished job to it.

request body

{
  "model": "kandinsky_6_lite",
  "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing.",
  "options": {
    "webhook_url": "https://your-app.com/varg-webhook"
  }
}

From Claude, ChatGPT or Cursor (MCP)

The varg MCP server, https://mcp.varg.ai/mcp, runs Kandinsky 6.0 Lite with call_tool. Sign in with varg, no API key to paste. How to connect it

call_tool

{
  "tool": "video",
  "input": {
    "model": "kandinsky_6_lite",
    "prompt": "A street violinist plays under a bridge at night, rain on the cobblestones, the melody echoing."
  },
  "wait": true
}