P-Video 2 Pro

Pruna’s highest-quality video model. Start from a prompt or a first frame, optionally pin the last frame, and choose Fast for quick drafts or Quality for the final take. 5–15 seconds.


Model id	`p-video-2-pro`
Media	video
Submit to	`POST /v1/videos`
Price	varies by tier and settings; `GET /v1/models/p-video-2-pro/estimate` quotes it
Typical time	about 30.0 s

Text → Video

Generate a video from a text prompt. Select it with "mode": "text_to_video", or leave mode out and the inputs decide. Required: prompt, duration_seconds
Optional: aspect_ratio, variant Resolution tiers: 768p, 480p (send as tier).

{
  "model": "p-video-2-pro",
  "prompt": "Tiny real SWAT officers raid a glowing toy-brick house in a child's bedroom, advancing tactically and entering in formation. One tense low-angle cinematic shot, warm house light, soft blue bedroom ambience, subtle tactical sound.",
  "mode": "text_to_video",
  "aspect_ratio": "16:9",
  "duration_seconds": 5,
  "variant": "speed",
  "tier": "768p"
}

Field	Allowed	Default
`aspect_ratio`	`16:9`, `9:16`, `4:3`, `3:4`, `3:2`, `2:3`, `1:1`	`"16:9"`
`duration_seconds`	5.0 – 15.0 seconds	`5`
`variant`	`speed`, `quality`, `cost`	`"speed"`

Image → Video

Animate a required first frame, with an optional last frame to control the ending. The images set the canvas, so aspect ratio does not apply. Select it with "mode": "image_to_video", or leave mode out and the inputs decide. Required: prompt, first_frame, duration_seconds
Optional: last_frame, variant Resolution tiers: 768p, 480p (send as tier).

{
  "model": "p-video-2-pro",
  "prompt": "Tiny real SWAT officers raid a glowing toy-brick house in a child's bedroom, advancing tactically and entering in formation. One tense low-angle cinematic shot, warm house light, soft blue bedroom ambience, subtle tactical sound.",
  "mode": "image_to_video",
  "duration_seconds": 5,
  "variant": "speed",
  "first_frame": "asset_…",
  "tier": "768p"
}

Field	Allowed	Default
`duration_seconds`	5.0 – 15.0 seconds	`5`
`variant`	`speed`, `quality`, `cost`	`"speed"`
`first_frame`	asset id (up to 1)
`last_frame`	asset id (up to 1)

Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/p-video-2-pro is always current.

Start here

Using the API

Choosing a model

Image models

Video models

Audio models

Agents and MCP

Text → Video

Image → Video

​Text → Video

​Image → Video

Text → Video

Image → Video