Palo Nano
A planned efficiency tier. No deployed adapter, dimensions, pricing, or latency promise is established by the current API.
Runtime status
Palo runtime status
Palo Nano, Palo Bloom, and Palo Research describe the model family and research direction. No live model adapter is attached to the hosted v1 customer memory path today. The current path uses a deterministic text fixture so the API contract, storage checks, usage ledger, and observability can be tested without implying model execution.
Model family status
Palo Bloom
Mpalo's experience-aware memory architecture in development. No Bloom model executes on the hosted v1 path.
Palo Research
A research direction for deeper representation and memory behavior. It is not a public production engine.
The current customer path
execution_mode=mock, provider=mpalo-local-mock, and
model_version=deterministic-lexical-v1 mean that the request ran through the current
deterministic service fixture. An unspecified model variant means no Palo model ran. The request
may still exercise storage, retrieval, rendering, usage, and operational recording.
| Capability | Status | Current behavior |
|---|---|---|
| Text persistence | available_mock | Submitted text can be retained after storage, consent, and policy checks. |
| Lexical retrieval | available_mock | Tenant-scoped deterministic ranking over retained text. |
| Stored-text rendering | available_mock | Selected retained text can be returned as context. |
| Embeddings and semantic search | not_deployed | No customer-facing vector representation or index is attached. |
| Traversal and mapping | contract_stage | Response and attribution shapes exist for wiring, not learned behavior. |
How to choose today
There is no public model-selection decision to make for the current v1 API. Use the managed reference path to integrate the contract and inspect its limits. Keep your downstream response model in your application. Do not select an engine name, infer a model from a key, or use current reference metrics as evidence for future model quality or pricing.
Was this page helpful?
Your feedback helps us improve our documentation.