Historical AI21 text-embedding service with query and document-segment roles. Its original vector dimensions, token ceiling and underlying checkpoint identity have not been verified.
The SDK exposes an operation, not a separately selectable checkpoint.
Access
Historical SDK POST route: /embed relative to the configured Studio base URL. No separately selectable model ID is exposed.
Regions
Not collected
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
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.
AI21 Studio embedding service (historical)
Not verified
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
How it works
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
Minimum reusable input
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
Lifetime & refresh
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
How to enable it
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
Usage fields
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
Billing rules
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
Limits & data boundaries
Not collected
No reviewed service-side cache contract. Client-local caching does not establish provider prompt caching.
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
The official SDK exposes a hosted task operation without a selectable checkpoint or downloadable weights. This is an explicitly managed component, not an independently established proprietary weight release.
