Pison Labs / Pison research models
Announced speech-recognition model for African language clusters and telephony audio; the research page says training.
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
No reviewed model-specific value; unknown is not unsupported.
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Not collectedNo immutable serving checkpoint established.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
The system processes eligible input and retains reusable state.
Reuse depends on matching input, session state and the cache policy.
Reusing state can reduce repeated work. Any charges follow the billing rules below.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
No model-specific inference-cache contract. Streaming buffers, file storage and cold-start loading are not prompt caching.
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 2026No 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.
Provider names an unreleased model in its research roadmap; terms reserve neural weights to Pison and licensors and prohibit extraction. Exact eventual artifact license and base-model ancestry remain unresolved; no public deployment is claimed.
Classification evidence (opens in a new tab)