Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Pruna AI: P-Video-2-Pro

P-Video-2-Pro is Pruna AI's quality-tier video generation model built on MiniMax H3, creating clips from text or from a first frame with an optional last frame. It handles multi-beat camera moves, heavy physics like water, fire, and fabric, coherent full-body motion, and two-shot dialogue with lip sync, generating audio with every clip. It offers cost, speed, and quality recipes, three levels of prompt expansion, durations from 5 to 15 seconds, and 480p or 768p output at 24 FPS.
Compare models
p-video-2-pro
AvailablePruna AIVideoAsync
Price
From $0.01
Modalities
Video

About P-Video-2-Pro

P-Video-2-Pro is the cinematic tier of Pruna AI's video line, built on MiniMax H3. It generates five-to-fifteen-second clips from text, or from a first frame with an optional last frame, and always includes generated audio. Pruna lists multi-beat camera moves, water, fire and fabric physics, full-body motion, and two-person dialogue with lip sync. Speed, quality, and cost recipes are selectable.

Where it works well

  • Audio is generated with every clip, including two-person dialogue with lip sync.
  • Pruna highlights heavy physics such as water, fire and fabric, and coherent full-body motion.
  • Three recipes let you favour speed, quality, or cost, and a prompt upsampler has off, turbo and max levels.
  • First-frame and last-frame images can pin the start and end of a shot.

When to choose another model

  • Output is limited to 480p or 768p at 24 fps; P-Video-2 reaches 1080p and 48 fps.
  • Audio cannot be supplied as input, so you cannot lock the clip to your own voiceover.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image to videoStart and end frames to videoText to videoTokenLab endpoint
    POST/v1/videos/generations
    curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "duration": 5,
      "operation": "text-to-video",
      "model": "p-video-2-pro",
      "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
    }'

Parameters

Image to video

ParameterValues and limitsDefaultNotes
duration≥ 5, ≤ 155Use an integer.
imageNot providedNot providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
image_urlNot providedNot providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
n11Use an integer.
operationNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 1 characters. Maximum length: 10000 characters.
resolution480p480pOnly 480p is offered.
seconds≥ 5, ≤ 155Use an integer.
seed≥ 0, ≤ 2147483647Not providedUse an integer.
start_imageNot providedNot providedFirst frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.

Start and end frames to video

ParameterValues and limitsDefaultNotes
duration≥ 5, ≤ 155Use an integer.
end_imageNot providedNot providedLast frame: a public image URL or a data URL. Required.
n11Use an integer.
operationNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 1 characters. Maximum length: 10000 characters.
resolution480p480pOnly 480p is offered.
seconds≥ 5, ≤ 155Use an integer.
seed≥ 0, ≤ 2147483647Not providedUse an integer.
start_imageNot providedNot providedFirst frame: a public image URL or a data URL. Required.

Text to video

ParameterValues and limitsDefaultNotes
duration≥ 5, ≤ 155Use an integer.
height480, 640, 704, 832480Use an integer. Use a listed width and height pair: 832x480 (480p, 16:9), 480x832 (480p, 9:16), 640x480 (480p, 4:3), 480x640 (480p, 3:4), 704x480 (480p, 3:2), 480x704 (480p, 2:3), 480x480 (480p, 1:1).
n11Use an integer.
operationNot providedNot providedNot provided
output_formatmov, mp4, webmmp4Not provided
promptNot providedNot providedMinimum length: 1 characters. Maximum length: 10000 characters.
seconds≥ 5, ≤ 155Use an integer.
seed≥ 0, ≤ 2147483647Not providedUse an integer.
width480, 640, 704, 832832Use an integer. Use a listed width and height pair: 832x480 (480p, 16:9), 480x832 (480p, 9:16), 640x480 (480p, 4:3), 480x640 (480p, 3:4), 704x480 (480p, 3:2), 480x704 (480p, 2:3), 480x480 (480p, 1:1).

Fields outside this contract are rejected.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to video · 480p

per second
Official price
$0.01
Verified price
—
Discount
—

Text to video · 768p

per second
Official price
$0.025
Verified price
—
Discount
—

Image to video · 480p

per second
Official price
$0.01
Verified price
—
Discount
—

Image to video · 768p

per second
Official price
$0.025
Verified price
—
Discount
—

Start and end frames to video · 480p

per second
Official price
$0.01
Verified price
—
Discount
—

Start and end frames to video · 768p

per second
Official price
$0.025
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open P-Video-2-Pro in Console with a prompt ready to edit or send.

Help me create with p-video-2-pro using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for
  • Text to Video
  • Cinematic shots

    Create camera moves with several beats, such as a push-in followed by a pan, from a single prompt.

  • Physics-heavy scenes

    Generate waves, flames, or flowing cloth that must move plausibly. Prompts can describe the motion in some detail.

  • Dialogue exchanges

    Produce a two-shot conversation with synchronized speech. Two speakers can be framed in one shot.

Prompt examples

A sailor and a lighthouse keeper argue on a storm-lashed pier; waves crash, the keeper shouts 'Come inside!'.

Start frame: a silk scarf on a balcony railing. The wind rises and the scarf lifts and flutters away.

Camera pushes through a burning workshop, then pans to a figure walking out in slow motion.

FAQ

What exactly is P-Video-2-Pro?

It is Pruna AI's quality-tier video model built on MiniMax H3. It generates clips from text or from a first frame, with an optional last frame, and includes synchronized audio in every result.

What lengths and resolutions are offered?

Pruna lists five to fifteen seconds, in 480p or 768p at 24 frames per second. For 1080p or longer clips, look at P-Video-2. Pricing and speed vary with length.

What are the recipes?

Speed (the default), quality, and cost. They shift the balance between turnaround, fidelity, and price for the same prompt, so you can test on speed and finish on quality.

What does prompt expansion do?

The prompt upsampler rewrites a short prompt into a fuller one. Pruna lists off, turbo (default) and max, and says it does not affect pricing.

Can I feed my own audio?

No, audio input is not exposed. The model produces its own sound. If you need a clip driven by your voiceover, use P-Video-2 or P-Video-Avatar.

How much does P-Video-2-Pro cost?

On TokenLab, P-Video-2-Pro costs $0.01-$0.025 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should P-Video-2-Pro use?

Use https://api.tokenlab.sh/v1/videos/generations for P-Video-2-Pro. The request example below shows the matching code shape.

Which operations does P-Video-2-Pro support?

P-Video-2-Pro supports Image to video, Start and end frames to video, Text to video. Select an operation above to see its endpoint and request example.

Compare P-Video-2-Pro

Guides that use P-Video-2-Pro

Sources

Reviewed Oct 2, 2026

More from Pruna AI

Related models