Microsoft AI / MAI-1-preview
Microsoft’s early in-house language model, publicly tested on LMArena and announced for selected Copilot text experiences in August 2025.
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Not collectedNo public API model selector documented.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Model-specific retention and training-use policy not collected.
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 endpoint-specific cache contract verified for this version.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 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.
Microsoft documents this as its internally developed MAI model, distributed through hosted Microsoft products or services. The reviewed materials provide no downloadable weights for this named model. Public Phi and MAI-DS-R1 families are not included by inference.
Classification evidence (opens in a new tab)