Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Pruna AI / P-Video

P-Video-2

Managed video-generation workflow from text, images or audio, with optional prompt-selected duration and standard or draft pricing.

Video generation
availableClosed-source managed componentVideo generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
7 of 23 specification fields collected
Output resolution720p, 1080pSee specification notes below
Clip durationRequested 1–20 seconds; omit to let the model choose. Audio overrides duration.See specification notes below
Input billingSee ratesPruna API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Maximum input tokens
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Maximum output
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Maximum prompt characters
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Reasoning
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Tool calling
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Structured output
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Streaming
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Batch processing
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Fine-tuning
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Context caching
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Knowledge cutoff
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Release date
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Parameters
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Architecture
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Languages
Not collected

Not established for this exact hosted workflow. Upstream open-model features and language-model capabilities are not inherited.

Base model
LTX license family referenced; exact checkpoint/version unresolved.Source for Base model (opens in a new tab)

The linked license index covers multiple LTX releases. No LTX parameter count, architecture or version is inferred for this workflow.

Input modalities
Text, Image, AudioSource for Input modalities (opens in a new tab)
Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Audio is delivered with the video, not a separate text-to-speech endpoint.

Video duration
Requested 1–20 seconds; omit to let the model choose. Audio overrides duration.Source for Video duration (opens in a new tab)
Output resolutions
720p, 1080pSource for Output resolutions (opens in a new tab)
Frame rates (fps)
24, 48Source for Frame rates (fps) (opens in a new tab)
Audio generation
Generated audio can accompany video. save_audio defaults to true; uploaded audio can condition the video.Source for Audio generation (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Pruna API

Provider source (opens in a new tab)
API model ID
p-video-2
Access
Native API documented; account and API key required. No inference job submitted.
Regions
Not established
API endpoint URL
POST https://api.pruna.ai/v1/predictionsSource for API endpoint URL (opens in a new tab)
Authentication
apikey and Model headers; parameters inside the input object.Source for Authentication (opens in a new tab)
Required request fields
promptSource for Required request fields (opens in a new tab)

Conditional speech requirements for avatar are recorded separately.

Model controls
View all 13 entries
  • prompt
  • duration
  • image
  • audio
  • resolution
  • fps
  • aspect_ratio
  • seed
  • draft
  • save_audio
  • last_frame_image
  • prompt_upsampling
  • disable_safety_filter
Source for Model controls (opens in a new tab)
Request quotas
250 requests/minuteSource for Request quotas (opens in a new tab)
Asynchronous generation
Asynchronous by default. Try-Sync=true waits up to 60 seconds; unfinished requests use prediction-status polling.Source for Asynchronous generation (opens in a new tab)
Result retrieval
GET /v1/predictions/status/{id}; retrieve generated media from the returned delivery URL.Source for Result retrieval (opens in a new tab)
Billing basis
Measured length of the finished video, reported in whole seconds; rounding rule is not specified. Audio-conditioned requests bill the audio-driven result length, not an overridden duration parameter.Source for Billing basis (opens in a new tab)
Seed control
Optional integer seed; numeric range not established for this route.Source for Seed control (opens in a new tab)
Documentation discrepancy
Draft prose claims half-price, but the explicit matrix lists $0.015 versus $0.025 at 720p and $0.03 versus $0.05 at 1080p. The captured OpenAPI omits this selector; guide-specific controls are retained.Source for Documentation discrepancy (opens in a new tab)
Duration controls
duration is optional, 1–20 seconds, without a fixed default. Omit it for prompt-selected length. Uploaded audio overrides the requested duration.Source for Duration controls (opens in a new tab)
Source audio handling
Input audio formats: FLAC, MP3 or WAV. save_audio defaults to true. An audio-specific duration or file-size ceiling is not established.Source for Source audio handling (opens in a new tab)
Input file formats
JPEG, PNG, WebP, FLAC, MP3, WAVSource for Input file formats (opens in a new tab)

Images use JPEG/PNG/WebP; uploaded audio uses FLAC/MP3/WAV.

Reference guidance
Optional initial image and last_frame_image. Input image determines aspect ratio; the aspect_ratio control is ignored when image is supplied.Source for Reference guidance (opens in a new tab)
Aspect ratios
16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 1:1Source for Aspect ratios (opens in a new tab)
Resolution controls
resolution defaults to 720p; choices 720p/1080p. fps defaults to 24; choices 24/48.Source for Resolution controls (opens in a new tab)
Prompt expansion
prompt_upsampling defaults to true.Source for Prompt expansion (opens in a new tab)
Generation controls
draft defaults to false; true selects a lower-quality preview.Source for Generation controls (opens in a new tab)
Content screening controls
Published disable_safety_filter default is true.Source for Content screening controls (opens in a new tab)

Recorded provider default, not a recommendation.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Video generation720p · standard1$0.025output video second
Video generation720p · draft2$0.015output video second
Video generation1080p · standard1$0.05output video second
Video generation1080p · draft2$0.03output video second

Rate conditions

  1. Native output-video seconds with draft=false. Uploaded audio may determine output duration. No minimum/rounding rule established.
  2. Native output-video seconds with draft=true. Explicit price matrix used; conflicts with generic half-price prose.
Pricing source (opens in a new tab)

Data & enterprise terms

Pruna terms retain customer rights in input/output and permit processing to provide the service, plus operational telemetry. Upstream model terms may apply. A universal retention period and zero-training guarantee are not established.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Pruna API

p-video-2
Not verified

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

How it works
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

Minimum reusable input
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

Lifetime & refresh
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

How to enable it
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

Usage fields
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

Billing rules
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

Limits & data boundaries
Not collected

No verified prompt-cache mechanism or cached-inference tariff. Asset uploads, conditioning and asynchronous predictions do not establish prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Pruna names this hosted video workflow and links the LTX license family. Exact upstream revision and any private post-training are not established. Included explicitly as a managed component; public LTX weights and Pruna optimization-library code are not counted as new private base models.

Classification evidence (opens in a new tab)

Sources reviewed