Kandinsky 6.0 Pro is Kandinsky Lab's flagship text-to-video model, generating high-resolution clips with cinematic motion and precise prompt adherence.
Every plan, free included. Runs spend your account’s credits.
The smallest request that works: the required fields only.
Percify APIcurl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "kandinsky-6-pro-t2v",
"input": {
"prompt": "A red fox running through fresh snow at sunrise"
}
}'9 fields in input, required first.
promptRequiredThe text prompt describing the video and its sound.
seedOptionalThe random seed used for the generation process.
aspect_ratioOptionalThe aspect ratio of the generated video.
generate_audioOptionalWhether to generate a synchronized audio track.
guidance_scaleOptionalClassifier-free guidance strength.
upscale_factorOptionalIf set, upscale the generated video by this factor with Kandinsky 6 video super-resolution. One of 2, 2.25 or 4; 2.25 turns the 480p output into 1080p.
$0.82/sFLUX 3 Video Extend continues input videos into new 5-20 second clips, using prompt guidance to control the next action, camera movement, visual style, motion continuity, and optional synchronized audio at 720P / 1080P output.
$0.34/sFLUX 3 Start-End-to-Video generates 5-20 second transition videos between required start and end images, using prompt guidance to control action, camera movement, visual style, motion continuity, and optional synchronized audio at 720P / 1080P output.
$0.34/sFLUX 3 Text-to-Video generates cinematic 5-20 second videos from text prompts, with coherent motion, cinematic composition, optional synchronized audio, and 720P / 1080P output for creative videos, social content, ads, and production workflows.
$0.06/sGemini Omni 1.1 Flash Text-to-Video creates short AI videos with synchronized audio from text prompts, supporting resolutions from 360P to 4K for social content, creative storytelling, marketing videos, and production workflows.
Pick a use case, run it in the playground, copy the call.
Every plan, free included. Runs spend your account’s credits.
negative_promptOptionalWhat to avoid in the video. Defaults to the model's built-in negative prompt.
num_inference_stepsOptionalThe number of denoising steps.
enable_prompt_expansionOptionalWhether to rewrite the prompt into a detailed video+audio description with the model's own Qwen2.5-VL text encoder before generating.