No verified current access to this original checkpoint.
Access
Historical documentation only. Original checkpoint availability, selector and price are not established.
Regions
Model-specific processing location not established in reviewed sources.
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.
Lelapa historical model card
Not verified
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
How it works
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Minimum reusable input
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Lifetime & refresh
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
How to enable it
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Usage fields
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Billing rules
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Limits & data boundaries
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
What the measurements say
isiZulu WER
Lelapa AI · provider-reported
0.457ratio
Published model-card evaluation, not independently reproduced and not a guarantee for current routing or different recordings. Version 1.0.0 card. Lower WER is better; general/call-center data for South African languages, government-domain African French data for French.
Published model-card evaluation, not independently reproduced and not a guarantee for current routing or different recordings. Version 1.0.0 card. Lower WER is better; general/call-center data for South African languages, government-domain African French data for French.
Published model-card evaluation, not independently reproduced and not a guarantee for current routing or different recordings. Version 1.0.0 card. Lower WER is better; general/call-center data for South African languages, government-domain African French data for French.
Published model-card evaluation, not independently reproduced and not a guarantee for current routing or different recordings. Version 1.0.0 card. Lower WER is better; general/call-center data for South African languages, government-domain African French data for French.
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 provider model card explicitly identifies proprietary model weights or a proprietary fine-tuned derivative. Current language routes may use newer unnamed checkpoints; catalog family labels are not invented API model IDs.
