Public /public routes: per-IP daily cap, numeric allowance not published. Bearer-authenticated routes: higher account-level limits, numeric cap not published. HTTP 429 for quota exhaustion; exponential backoff with jitter is recommended.Source for Request quotas (opens in a new tab)
Usage metering
Paid rates follow the plan/order form; no reviewed numeric speech, entity-extraction or token tariff. An insufficient-balance error does not establish a unit price.Source for Usage metering (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Task route and language code are not immutable checkpoint selectors.
Access
POST https://api.pindo.io/ai/ner/{lang}/public; lang = rw, en; JSON text, lang and optional labels. No bearer token; per-IP daily cap (numeric quota unpublished). HTTP 400 can indicate invalid input, 409 insufficient balance, 429 rate limit, 500 server error.
Regions
Policy describes international processing; exact inference region is not specified.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Privacy permits processing audio, transcripts, call metadata and usage logs; recordings/transcripts may be retained on enterprise customer instruction. No training on enterprise call content for general-purpose models without written customer instruction; policy separately describes speech and agent quality improvement. Retention depends on purpose and customer instructions, with no fixed TTL. Cloud, telephony, speech-processing and analytics providers may process data across regions. This is not universal zero retention or a blanket no-training guarantee.
Task route and language code are not immutable checkpoint selectors.
Access
POST https://api.pindo.io/ai/ner/{lang}; lang = rw, en; JSON text, lang and optional labels. Authorization: Bearer token; higher account-level limits (numeric quota unpublished). Token rotation in account Security revokes the previous token immediately. HTTP 400 can indicate invalid input, 409 insufficient balance, 429 rate limit, 500 server error.
Regions
Policy describes international processing; exact inference region is not specified.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Privacy permits processing audio, transcripts, call metadata and usage logs; recordings/transcripts may be retained on enterprise customer instruction. No training on enterprise call content for general-purpose models without written customer instruction; policy separately describes speech and agent quality improvement. Retention depends on purpose and customer instructions, with no fixed TTL. Cloud, telephony, speech-processing and analytics providers may process data across regions. This is not universal zero retention or a blanket no-training guarantee.
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.
Pindo VoiceAI API
Not verified
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
How it works
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Minimum reusable input
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Lifetime & refresh
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
How to enable it
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Usage fields
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Billing rules
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Limits & data boundaries
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
Pindo VoiceAI API
Not verified
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
How it works
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Minimum reusable input
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Lifetime & refresh
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
How to enable it
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Usage fields
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Billing rules
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not prompt caching.
Limits & data boundaries
Not collected
No inference-cache contract published in reviewed sources. Uploaded/generated file storage and call recording retention are not 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
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
Proprietary hosted service; Pindo and its licensors reserve service/model IP and restrict reverse engineering. Specific checkpoint identity and artifact licensing are undisclosed, so this is not claimed as an independently verified closed-weight release.
