Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Pison Labs / Pison managed APIs

Pison Voice Agents

Beta managed conversational voice workflow for telephony and WhatsApp.

previewClosed-source managed componentVoice conversation
Official documentation (opens in a new tab)Reviewed 16 Oct 2026
5 of 19 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingSee ratesPison Labs API / platform
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No reviewed model-specific value; unknown is not unsupported.

Maximum input tokens
Not collected

No reviewed model-specific value; unknown is not unsupported.

Maximum output
Not collected

No reviewed model-specific value; unknown is not unsupported.

Parameters
Not collected

No reviewed model-specific value; unknown is not unsupported.

Release date
Not collected

No reviewed model-specific value; unknown is not unsupported.

Knowledge cutoff
Not collected

No reviewed model-specific value; unknown is not unsupported.

Tool calling
Not collected

No reviewed model-specific value; unknown is not unsupported.

Structured output
Not collected

No reviewed model-specific value; unknown is not unsupported.

Streaming
Not collected

No reviewed model-specific value; unknown is not unsupported.

Batch processing
Not collected

No reviewed model-specific value; unknown is not unsupported.

Fine-tuning
Not collected

No reviewed model-specific value; unknown is not unsupported.

Reasoning
Not collected

No reviewed model-specific value; unknown is not unsupported.

Context caching
Not collected

No reviewed model-specific value; unknown is not unsupported.

Base model
Not collected

No reviewed model-specific value; unknown is not unsupported.

Request quotas
Plan-wide simultaneous requests: Free 2, Individuals 10, Pro 30, Business 100. These are concurrency limits, not requests/second or context limits. 429 includes Retry-After.Source for Request quotas (opens in a new tab)
Usage metering
Per conversational agent minute; plan allowances and overage rates apply.Source for Usage metering (opens in a new tab)
Published price
Monthly plan allowances (agent minutes): Free 30, Individuals 1,000, Pro 6,000, Business 40,000. Paid plans USD 29/99/499 or NGN 45,000/150,000/750,000 monthly. Overage charges are additional; the two currency schedules are published prices, not conversions.Source for Published price (opens in a new tab)

Allowance quantities come from the pricing page; contract invoice controls currency and FX terms.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Pison Labs API / platform

Provider source (opens in a new tab)
API model ID
Not collected

No immutable serving checkpoint established.

Access
Advertised beta platform workflow; no reviewed direct API route or native model selector.
Regions
Policy describes Lagos core deployment with potential London/other edge transit. Strict Nigerian routing requires private tenancy.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 16 Oct 2026
CategoryUsageRateUnit
Individuals plan overageIndividuals overage1$0.035agent minute
Pro plan overagePro overage2$0.03agent minute
Business plan overageBusiness overage3$0.025agent minute
Individuals plan overageIndividuals overage4NGN 55.00agent minute
Pro plan overagePro overage5NGN 46.00agent minute
Business plan overageBusiness overage6NGN 38.00agent minute

Rate conditions

  1. Additional usage only after the Individuals monthly allowance. Requires the $29/month plan; included quota and subscription are not replaced by this marginal charge. USD schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
  2. Additional usage only after the Pro monthly allowance. Requires the $99/month plan; included quota and subscription are not replaced by this marginal charge. USD schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
  3. Additional usage only after the Business monthly allowance. Requires the $499/month plan; included quota and subscription are not replaced by this marginal charge. USD schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
  4. Additional usage only after the Individuals monthly allowance. Requires the ₦45,000/month plan; included quota and subscription are not replaced by this marginal charge. NGN schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
  5. Additional usage only after the Pro monthly allowance. Requires the ₦150,000/month plan; included quota and subscription are not replaced by this marginal charge. NGN schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
  6. Additional usage only after the Business monthly allowance. Requires the ₦750,000/month plan; included quota and subscription are not replaced by this marginal charge. NGN schedule as published, not a conversion. Invoice and applicable FX terms control billing. Beta workflow; docs say no SLA.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider privacy policy states ephemeral streaming audio unless enterprise asynchronous storage or custom logging is enabled; request metadata is retained 30 days, account records active tenure plus 7 years, and custom voices until deletion with a 30-day purge window. Terms restrict the no-training guarantee to paid API payloads and public foundation models, with opt-in exceptions. Pricing retention tiers and broader policy headlines need reconciliation. Lagos core infrastructure and possible London/other edge transit are described; strict Nigerian routing requires private tenancy. These are provider claims, not independent compliance certification.

Read the service policy (opens in a new tab)

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.

Pison Labs API / platform

Not verified

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

How it works
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

Minimum reusable input
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

Lifetime & refresh
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

How to enable it
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

Usage fields
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

Billing rules
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.

Limits & data boundaries
Not collected

No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading 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

Managed API or workflow under proprietary service terms; backing checkpoint identity is not established. Not counted as an independently verified private foundation-model release.

Classification evidence (opens in a new tab)

Sources reviewed