One API call. A panel of models behind it.

Moamao turns a single prompt into a structured deliberation — parallel drafts, cross-model critique, judged synthesis — and returns one answer with a trace you can audit. Here is each piece in detail.

The pipeline: three layers, in order.

A run is a real sequence: the output of each layer is the input to the next. The numbering below is the order your prompt travels.

01
Propose
"panel": "balanced-4" // or name each seat explicitly
Your prompt fans out to the panel — up to four proposer models drawn from different provider families (claude, gpt, gemini, llama). Each answers independently and in parallel, with no visibility into the others. Independence matters here: correlated drafts would give the later layers nothing to work with. Because the fan-out is parallel, layer one takes roughly as long as the slowest single model, not four calls in sequence.
Panel makeup is yours to set — pick a preset, or name exact models per seat. Cross-provider panels are the default because models trained on different data fail in different places.
02
Critique
"layers": 2 // propose → critique
Every proposer now reads the other three drafts. Each model flags claims it disagrees with, points out gaps, and revises its own answer in light of what the rest of the panel wrote. This is where a single model’s hallucination tends to die: an invented citation or a wrong API signature rarely survives review by three models that didn’t make the same mistake.
The critique layer also runs in parallel — four revised drafts come back in one round trip. You can add layers for harder problems or drop to one for speed; two is the default.
03
Aggregate
"aggregator": "auto" // or pin a specific judge
A judge model reads the revised drafts and synthesizes one final answer — not a vote, not a concatenation, but a new response built from the strongest parts of each draft. Alongside the answer it records disagreement notes: the places where the panel didn’t converge, so you can see exactly where confidence is thin.
Set the aggregator explicitly or leave it on auto and Moamao picks a judge suited to the task. The judge streams as it writes, so the final answer arrives like a chat response.

Smart routing: not every prompt deserves a panel.

Before a run starts, Moamao scores the prompt. Simple, factual, or low-stakes requests — a date format, a one-line rewrite, a lookup — skip the panel entirely and go to a single fast model. You get the answer in one model's latency instead of two sequential layers, and you pay a fraction of a run instead of a full mixture.

Anything ambiguous, high-stakes, or genuinely hard goes to the full panel. The routing decision is recorded in the trace, so you can always see why a request went where it did — and you can force the panel on any request if you disagree with the router.

In practice this is what makes mixture economics work: the panel's cost and latency are spent only on the prompts where four models beat one.

Bring your own keys: your provider accounts do the model work. We orchestrate.

BYOK is the default and the honest way to run a mixture today: you connect your Anthropic, OpenAI, Google, and open-weights provider keys, and every model call runs on your accounts, your rates, and your rate limits.

How keys are stored

Keys are encrypted at rest, held per provider, and used only to place the calls your runs require. They are never logged, never shared between customers, and never used for anything resembling training.

What Moamao charges

An orchestration fee per run — that's it. The model usage itself lands on your provider invoices at whatever rates you negotiated. Two bills, both readable: your providers meter tokens, we meter runs.

Moamao Cloud — live

Don't want to manage four provider accounts? Moamao Cloud is our managed mixture endpoint — it runs the full mixture on managed capacity with zero provider setup, metered per token. Every plan includes a monthly Moamao Cloud credit equal to its price.

Traces and observability: every run leaves a record you can interrogate.

A mixture you can't inspect is just a slower black box. Moamao stores the full deliberation so the answer is never the only artifact.

Replay any run

Every draft, critique, and judge decision is stored per run. Open a trace and step through the full sequence — what each model said in layer one, how it revised in layer two, and what the judge kept.

Per-model attribution

The trace marks which panel member contributed which part of the final answer. When an answer is wrong, you can see whether one model misled the judge or the whole panel agreed on the error.

Disagreement notes

The judge records where the panel split and how it resolved the split. High-disagreement runs are your signal to double-check — the seams are visible instead of smoothed over.

Retention you control

Traces are encrypted at rest and never used for training. Keep them for auditing, or turn on zero-retention mode and Moamao discards run content after the response is delivered.

Panel presets: start from a tuned panel.

Presets are starting points, not walls — every field is overridable per request, and custom panels are available on paid plans.

Preset	Panel makeup	Best for
code-review	Two strong coding models + two generalists, 2 layers, code-tuned judge	Reviewing diffs, migration plans, API designs — anywhere a missed edge case is expensive
research	Four models across all four provider families, 2 layers, citation-strict judge	Fact-heavy questions where cross-checking claims matters more than speed
longform	Three writing-strong models, 2 layers, style-preserving judge	Drafts, documentation, and editing passes that need one coherent voice at the end
balanced-4	One model from each provider family, 2 layers, auto judge	The default. General-purpose prompts where you want maximum viewpoint diversity

What a run costs: one line on the invoice.

With BYOK, model usage stays on your provider bills and Moamao charges a flat orchestration fee per run. With Moamao Cloud — our managed mixture endpoint — tokens are metered per token across the whole mixture, and runs (BYOK) and tokens (Moamao Cloud) both appear on one Moamao invoice. Routed-to-single-model requests count as a quarter run. Failed runs don't count at all. Beta plans start at $0.

See beta pricing

terminal

POST https://api.moamao.com/v1/runs
Authorization: Bearer $MOAMAO_KEY

{
  "panel": "balanced-4",
  "input": "...",
  "layers": 2,
  "aggregator": "auto"
}

// billed: 1 run
// (0.25 if routed to a single model)

Open beta: stop betting everything on one model.

Create a free account, generate an API key, and run your first mixture in minutes — or watch it work in the playground first. BYOK from day one.

Create a free account Try the playground