Concepts

Nine terms cover the whole system. Each maps directly to a field in the API reference.

Run

A run is one orchestrated answer — the unit of work and the unit of billing. You send one prompt; Moamao fans it out to a panel, runs the layers, aggregates, and returns one answer with a trace. Whatever happens inside — four models, two layers, a judge — it's one run on your invoice. A prompt that smart routing sends to a single fast model counts as a quarter of a run.

Panel

The panel is the set of models that answer your prompt — up to four proposers drawn from different provider families (claude, gpt, gemini, llama). Mixing providers is the point: models trained on different data fail in different places, so their blind spots cancel out. You can name a preset or define the panel inline:

{
  "panel": {
    "proposers": ["claude-*", "gpt-*", "gemini-*", "llama-*"]
  }
}

Proposer

A proposer is one model on the panel. In layer 1 each proposer answers your prompt independently and in parallel, without seeing the others. In layer 2 the same proposers switch roles: each one reads the other drafts and revises its own.

Layer

Layers are the sequential stages of a run; the calls inside each layer run in parallel. Layer 1 is propose: independent drafts. Layer 2 is critique: each proposer reads the others' drafts, flags disagreements, and revises — weak claims get challenged before anything reaches the judge. layers: 2 (the default) means propose then critique; layers: 1 skips critique for a faster, cheaper run.

"layers": 2  // 1 = propose only, 2 = propose + critique

Aggregator (judge)

The aggregator — the judge — is the model that reads the final layer, synthesizes one answer, and records where the panel disagreed. The answer it ships is often one no single panelist produced alone. "aggregator": "auto" lets Moamao pick a judge suited to the prompt; you can also pin a specific model.

Trace

The trace is the run's complete record: every draft, every critique, and the judge's decision, each tagged with the model that produced it, plus the disagreements the judge recorded. Traces are replayable, so you can audit any answer after the fact. They're encrypted at rest and never used for training, and a zero-retention option discards them once the response is delivered.

Smart routing

Not every prompt deserves a mixture. Smart routing inspects each request and sends easy ones — lookups, formatting, short transformations — to a single fast model instead of the full panel. Routed requests are billed as a quarter of a run, and the trace says the request was routed so nothing is hidden. You only pay mixture latency and cost when the question earns it.

Moamao Cloud

Moamao Cloud is our managed mixture endpoint: the zero-setup compute mode that runs the full propose–critique–aggregate mixture on managed capacity, so you never manage a provider. Select it per request with "compute": "moamao-cloud" (the default is "byok"). It's metered per token — input plus output across the whole mixture — and every plan includes a monthly Moamao Cloud credit equal to its price. Availability is honest, not an SLA: it runs on managed capacity that may queue briefly when demand is high, and the playground shows live status. BYOK runs stay billed per run on your own provider rates; the two modes can be mixed request by request.

Preset

A preset is a named, tuned panel configuration — proposers, layers, and judge chosen for a job — so "panel": "balanced-4" is all most requests need. Current presets: balanced-4 (general-purpose default), code-review, research, and longform. List them programmatically with GET /v1/panels.

Ready to call it? The API reference documents every field, error, and limit.