Edits live video using a reference image for style transfer, clothing, character or background replacement. Media runs over RTC, with live editing changes sent over a separate control channel.
Frame-aligned attention over incoming video, with persistent reference conditioning; source frames are consumed with corresponding generated frames. TurboDiffusion/TurboServe acceleration is described in research.Source for Architecture (opens in a new tab)
Create /live/s_editing/realtime, initialize /live/ws/live/connect, publish input and subscribe to the rendered RTC stream. Query /live/v1/lives/{live_id} for usage.Source for Request mode (opens in a new tab)
Up to five unique RTMP addresses; each begins rtmp:// and is at most 2,048 characters. Duplicate URLs are removed. A push URL cannot be shared by simultaneous sessions.Source for RTMP relay limits (opens in a new tab)
One credit per billed live second, from successful conn_init_ack until hangup. Connecting WebSocket/RTC alone and changing reference images are not separately billed.Source for Usage metering (opens in a new tab)
Up to five unique RTMP addresses; each begins rtmp:// and is at most 2,048 characters. Duplicate URLs are removed. A push URL cannot be shared by simultaneous sessions.Source for RTMP relay limits (opens in a new tab)
Authentication
Editing-specific docs say raw vda_<key> without Token; shared overview says Token prefix. Browser WebSocket may use short-lived client_secret instead.Source for Authentication (opens in a new tab)
Minimum starting balance
Not collected
An insufficient-credit error is documented, but the Editing creation threshold is not specified.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Video generation
Live video editing1
$0.005
second of live editing
Service add-on
Concurrency add-on2
$2,080.00
additional concurrent slot per month
Rate conditions
1 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Billed from on_live initialization success through hangup. WebSocket/RTC connection alone and reference switches do not incur separate charges. Final billed_seconds/credits_cost are authoritative.
416000 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Five concurrent sessions included per account; added capacity is charged separately from live usage.
Up to five unique RTMP addresses; each begins rtmp:// and is at most 2,048 characters. Duplicate URLs are removed. A push URL cannot be shared by simultaneous sessions.Source for RTMP relay limits (opens in a new tab)
Authentication
Editing-specific docs say raw vda_<key> without Token; shared overview says Token prefix. Browser WebSocket may use short-lived client_secret instead.Source for Authentication (opens in a new tab)
Minimum starting balance
Not collected
An insufficient-credit error is documented, but the Editing creation threshold is not specified.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Video generation
Live video editing1
CN¥0.03125
second of live editing
Service add-on
Concurrency add-on2
CN¥13,000.00
additional concurrent slot per month
Rate conditions
1 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. Billed from on_live initialization success through hangup. WebSocket/RTC connection alone and reference switches do not incur separate charges. Final billed_seconds/credits_cost are authoritative.
416000 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. Five concurrent sessions included per account; added capacity is charged separately from live usage.
Account-specific training use and input-retention terms remain unverified.
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.
Vidu API · international · editing
Not verified
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
How it works
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Minimum reusable input
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Lifetime & refresh
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
How to enable it
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Usage fields
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Billing rules
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Limits & data boundaries
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Vidu API · mainland China · editing
Not verified
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
How it works
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Minimum reusable input
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Lifetime & refresh
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
How to enable it
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Usage fields
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Billing rules
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
Limits & data boundaries
Not collected
No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 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
Qualified closed-weight classification inference from the named Vidu hosted model, official API/research descriptions and operator proprietary-service terms. Public client code and inference libraries are not model weights. Exact private/public checkpoint lineage remains unverified.
