AIVA’s neural audio codec supplies discrete representations for music modeling. It is a research component, with no standalone customer endpoint verified.
No model-specific numeric rate verified. Existing website subscriptions are not mapped to these research models.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The public product EULA requires a separate agreement for API access and grants training rights over uploaded influences. Research beta terms may differ; no model-specific retention or residency guarantee is verified.
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.
AIVA · internal research
Not verified
No model-specific cache API or billing contract verified.
How it works
Not collected
No model-specific cache API or billing contract verified.
Minimum reusable input
Not collected
No model-specific cache API or billing contract verified.
Lifetime & refresh
Not collected
No model-specific cache API or billing contract verified.
How to enable it
Not collected
No model-specific cache API or billing contract verified.
Usage fields
Not collected
No model-specific cache API or billing contract verified.
Billing rules
Not collected
No model-specific cache API or billing contract verified.
Limits & data boundaries
Not collected
No model-specific cache API or billing contract verified.
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 inference: AIVA identifies this as its own internally developed model in a research announcement describing selective private-beta access, while its official EULA restricts derivation of underlying technology and requires separate API agreements. Reviewed official pages provide no weight download or open license for this model. This is not an explicit per-checkpoint closed-weight declaration, and public metadata searches are not exhaustive. It is not classified solely from generated-music copyright terms.
