Charge uses the measured finished-video length. Omitted mode is speed. List prices apply at this October 15 review; the advertised 50% promotion ended October 13, 2026.Source for Billing basis (opens in a new tab)
Catalog range starts at $0.02/s, but the detailed mode table includes 480p cost at $0.01/s. Use the detailed list-price matrix; do not carry forward the expired 50% discount. Captured OpenAPI 0.6.0 omits the selector.Source for Documentation discrepancy (opens in a new tab)
Pruna terms explicitly identify MiniMax H3 and pass through model-specific restrictions. Exact H3 revision and post-training are not established.Source for Model terms (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 15 Oct 2026
Category
Usage
Rate
Unit
Video generation
480p · cost1
$0.01
output video second
Video generation
480p · speed1
$0.02
output video second
Video generation
480p · quality1
$0.04
output video second
Video generation
768p · cost1
$0.025
output video second
Video generation
768p · speed1
$0.035
output video second
Video generation
768p · quality1
$0.075
output video second
Rate conditions
List price after the promotion ending October 13, 2026. Measured output seconds; prompt_upsampler does not change this rate. Exact rounding/minimum not established.
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.
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-pro
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 explicitly describes a hosted workflow based on MiniMax H3. The exact recipe and checkpoint changes are not established, so this is a managed deployment record, not an additional claimed private foundation model or a duplicate of the public H3 base.
