Kandinsky5 Text to Video Distill API

Kandinsky5 distilled text-to-video model for faster generation.

Modalities
TextVideo
Price
$0.01per second
Clip length
5 to 10 s
Released
Nov 24, 2025

Kandinsky5 Text to Video Distill overview

Duration
Aspect ratio

Kandinsky5 Text to Video Distill specs

Model ID
sber-ai/kandinsky5-distill-t2v
Developer
Sber AI
Input
Text
Output
Video
Endpoint
POST https://api.aimlapi.com/v2/video/generations

What is Kandinsky5 Text to Video Distill API?

Kandinsky5 Text to Video Distill API Pricing
- Pricing on request

Where to Use Kandinsky5 Text to Video Distill

Short-form video generation
Create clips for social, ads, and product demos from text or image prompts.

Use cases

Fast text-to-video generation is documented as a use case for this model, and the documentation says it is designed for generating videos from a prompt with no sound.

It is also suited to low-latency generation, because the distilled variant is described as a lightweight model for fast, high-quality text-to-video generation.

Another documented use case is creating short clips, since the model documentation exposes 5-second and 10-second video-length options.

Kandinsky5 Text to Video Distill API pricing

Kandinsky5 Text to Video Distill pricing in US dollars
UsagePriceUnit
Video generation$0.01per second

The final price depends on request parameters such as resolution or duration.

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Kandinsky5 Text to Video Distill vs other video models: prices

AI/ML API rates for 5 models, per second.

AI/ML API prices in USD per second
ModelPer second
Kandinsky5 Text to Video Distill$0.01
HunyuanVideo Foley$0.01
Kandinsky5 Text to Video$0.016
Wan 2.6 Image to Video Flash$0.025
Krea WAN 14B Text to Video$0.025

How to use the Kandinsky5 Text to Video Distill API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v2/video/generations' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "sber-ai/kandinsky5-distill-t2v",
  "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'

The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.

Related articles

All posts

Kandinsky5 Text to Video Distill FAQ

What inputs and outputs does Kandinsky5 Text to Video Distill support?

Kandinsky5 Text to Video Distill takes text as input and returns video.

How much does Kandinsky5 Text to Video Distill cost?

Kandinsky5 Text to Video Distill costs $0.01 per second on AI/ML API, billed as you go with no subscription.

How is Kandinsky5 Text to Video Distill billed?

Kandinsky5 Text to Video Distill costs $0.01 per second on AI/ML API, billed as you go with no subscription.

Who created Kandinsky5 Text to Video Distill?

Kandinsky5 Text to Video Distill was built by Sber AI.

How do I call Kandinsky5 Text to Video Distill on AI/ML API?

Use sber-ai/kandinsky5-distill-t2v as the model id on AI/ML API.

Is Kandinsky5 Text to Video Distill available through a single API key?

Yes. Kandinsky5 Text to Video Distill is served through AI/ML API, so the same key and endpoint format used for other models applies.

What is the Kandinsky5 Text to Video Distill model ID?

Use sber-ai/kandinsky5-distill-t2v as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.

Start building with Kandinsky5 Text to Video Distill

Kandinsky5 Text to Video Distill API

sber-ai/kandinsky5-distill-t2v

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v2/video/generations' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "sber-ai/kandinsky5-distill-t2v",
  "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'