Collective Intelligence: The Next Frontier of AI
Thousands of AI models in one collective. Each request draws on just a handful.
Ailin¹ Collective Intelligence
Ailin¹ is a collective model, not a router and not an orchestrator. Drawing on a catalog of 101,004 AI models, each request fans out to a handful that reason, debate, and cross-check each other behind a single prompt. On objectively verifiable tasks, that collective answered correctly 97% of the time, beating every individual frontier model we tested (68 to 82%).
Proven against the frontier, in the open
We tested the collective against GPT-5.5-pro, Claude Opus 4.8, Gemini 3.1 Pro, and Grok 4.3, graded by objective, machine-checked answers instead of taste. On verifiable tasks, the collective answered correctly 97% of the time. Every flagship model we tested landed between 68% and 82%. The raw data and scripts are public: run the benchmark yourself.
Ailin¹ Instinct
Every request runs through the same routing cascade before a single model is called. Name exactly what you want, and it's honored immediately. Say nothing, and the cascade decides.
State-of-the-Art Isn't a Black Box. It's a Dial You Control.
Five aliases span the full range, from an instant single model to five-model consensus. Two fields, max_cost and quality_target, set the boundaries. Ailin Instinct never crosses them.
Most platforms hand you a model list and call it a choice. Ailin¹ hands you a dial: how good the answer needs to be, and what you're willing to spend to get it, both explicit, both enforced before a model is ever called. max_cost is a hard ceiling, not a suggestion: if the strategy that would run is estimated to cost more than your ceiling, the request fails immediately with 400 strategy_budget_exceeded instead of quietly overspending. quality_target is the paired floor; the router escalates only as far as it needs to clear it.
| Alias | Optimizes for | Typical cost | Reach for it when |
|---|---|---|---|
| ailin-auto | Balanced fit, decided per request | Normal | No specific reason to pick anything else (the default) |
| ailin-best | Quality, cost unbounded | Highest | Being wrong costs more than being expensive |
| ailin-fast | Latency, single model | Low | The interface needs to feel instant |
| ailin-economy | Cost, hard ceiling enforced | Lowest | High-volume background work |
| ailin-consensus | Correctness via independent cross-checking | Higher, on purpose | A silently wrong answer is the failure mode you're paying to eliminate |
Every response reports where the dial actually landed: strategy_used, models_used, cost_usd. Not a promise. A receipt.
How Instinct Decides: The Five-Layer Cascade
A layered cascade, evaluated fastest-first. Each request resolves as early as it safely can, so simple requests settle fast while harder ones draw on the deeper layers.
-
Explicit routing
You named it, an alias, a model, or a strategy, so this layer resolves the request instantly. It always wins over every layer below it.
-
Semantic triage
Classifies the task, latency budget, volume pattern, and expected output shape, and maps it to a fitting strategy before any model runs.
-
Configuration archive
Unlocks with usage historyReuses whatever has historically worked best for that exact task niche, once enough history exists.
-
Cost / quality / latency frontier
Unlocks with usage historyOptimizes the three-way trade-off directly when no historical shortcut applies yet.
-
Learned preference model
Unlocks with usage historyWeights strategies by their real, measured outcomes over time, refining the cascade's own defaults.
Layers 3 to 5 need at least 5 recorded outcomes for a given task niche before they activate; until then, the same deterministic, auditable heuristic that always runs layers 1 and 2 makes the call.
32 Strategies, Grounded in Research
Every one auditable, spanning a single routed model up to nine-agent swarms exploring a problem in parallel. About 11 are reachable automatically today; the rest are explicit-only, fully functional the moment you name them.
Condorcet's Jury Theorem (1785): majority vote across 3 to 5 models, with a diversity floor so agreement can't come from cloned reasoning.
Hong and Page's Diversity Prediction Theorem (PNAS, 2004): assembles a team that maximizes cross-axis diversity by construction.
Models argue across structured rounds with a moderator.
Parallel exploration, auto-selected by triage for open-ended design and architecture work.
Convergence through a shared artifact rather than a vote, auto-selected by triage for high-complexity writing.
Independent multi-role review before an answer ships, addressable directly for verification-heavy requests.
Three coordinated roles cross-check one another end to end, addressable directly by name.
- Auto-selectable
- Most likely to be picked automatically by the routing cascade.
- Explicit-only
- Real and running, addressed directly via the strategy:tier syntax.
- Shadow / experimental
- Under continuous evaluation alongside live traffic, rarely selected automatically yet.
None of these are ad hoc. Every strategy in the catalog maps to a specific, named result in coordination or collective-decision research, not an internal guess dressed up as science.
You Don't Pick the Model. Ailin Instinct Does.
Simplicity when the task is simple. Depth when it isn't. You set the boundaries, Ailin Instinct decides within them, and one field always overrides it.
You never have to decide whether a request needs one model or five. Every request runs through Ailin Instinct, the same routing cascade behind ailin-auto, before a single model is called. Know exactly what you want? Name it: an alias like ailin-fast, a specific model, or strategy: "single", and Ailin Instinct honors it immediately, no negotiation, no added latency. Say nothing, and the cascade reads the task itself and picks a shape that fits it. Running a single model through Ailin isn't a fallback or a downgrade. It's a first-class path Ailin Instinct reaches for constantly, on purpose.
What about creative work and refactors?
Here we want to be precise, not just reassuring. In our own strategy comparisons, on a small set of open-ended tasks, a single well-chosen model outscored the full collective on every creative-writing trial (0 wins to 3 losses) and every refactoring trial (0 wins to 2 losses) we ran. That's a small sample, and we're not going to dress it up as a landslide: it's a signal, not a law, and the scoring method we used is known to favor single-voice prose on open-ended tasks. We're citing it because it matches something practitioners already suspect: forcing five models to agree on a creative brief or a refactor plan can sand down exactly the point of view that made it good.
Single model
One consistent voice, start to finish. Lower cost, lower latency, and exactly as reachable as the alternative.
ailin-fast
Multi-model collective
Independent verification: a second model checking the first one's work before you see an answer.
ailin-consensus
You don't choose between simple and thorough by memorizing when to use which. You say what you know, Ailin Instinct fills in what you didn't, and the override is always exactly one field away.
Amplitude, not just access
The Catalog Is the Advantage
101,004 models. Dozens of providers. One endpoint. Most AI platforms hand you a shortlist curated last quarter and call it a catalog. Ailin¹ indexes the live market continuously: new models are discovered as providers release them, automatically profiled for capability, cost, and latency, and folded into the catalog without a migration, a deployment, or a support ticket on your side.
-
Always current
New models go live the day they're discovered, not the day a roadmap gets around to them.
-
Full-spectrum
Text, vision, audio, and embeddings in the same catalog, behind the same endpoint.
-
No manual curation
Nobody is hand-picking which models make the cut. The catalog is what the market actually offers, indexed continuously.
Why a collective beats a single model
The strongest single model is still one point of training, one architecture, and one point of failure. Coordinate many well, and those limits disappear.
Resilience
One provider's outage never becomes your outage. The collective routes around degraded models and failures automatically, and every request still ships with full provenance.
Evaluation diversity
Different models trained on different data catch each other's mistakes. Disagreement becomes a quality signal, not a bug.
Anti-concentration
No vendor lock-in. The collective decouples your product from any single provider's roadmap, pricing, or policy.
Reduced bias
Architecturally diverse models dilute any one model's blind spots and training biases.
Dynamic specialization
The right specialist for the right task: reasoning, code, vision, long-context, or low-latency, elected in real time for every request.
Frequently asked questions
Straight answers, with the field, file, or number behind each one.
Integration & basics
chat/completions, responses, embeddings, models) is drop-in compatible, with an additive ailin_metadata block carrying decision provenance. Point your existing client at the Ailin¹ endpoint, swap the auth header, and the same request shape works.Ailin¹ Instinct & strategies
ailin-auto (balanced default, let the cascade decide), ailin-best (quality first, cost unbounded), ailin-fast (latency first, single model), ailin-economy (cost first, hard ceiling enforced), ailin-consensus (correctness via independent cross-checking). Start with ailin-auto. Reach for another only when you know something the router doesn't.<strategy>:<tier>, for example consensus:large, locking in the exact mechanism and price tier.ailin-fast, strategy: "single"), and the same one field gets you independent multi-model verification (expert-panel, tri-role-collective) if that's what you actually want instead.Cost & accountability
max_cost hard-caps spend before any model is called; if the estimated cost of the strategy that would run exceeds it, the request fails with 400 strategy_budget_exceeded instead of silently overspending. quality_target is the paired floor. Every response reports the real number back: ailin_metadata.cost_usd, with a line-item breakdown. Multi-model strategies cost measurably more, by 2 to 3 orders of magnitude in our own measurements; the ceiling and the receipt are how you keep that under your control, not ours.ailin_metadata.final_decider_model_id, the exact model that produced your answer, plus final_decider_role (primary, synthesizer, fallback, or cache) and a full subcalls[] array listing every participant with its own cost, latency, and outcome. If you're escalating a quality issue to a provider, that identifier is what matters, not "the Ailin API."Evidence & trust
See It For Yourself
The documentation covers the full API surface. The repository holds the coordination engine itself, the benchmark scripts, and the raw data behind every number on this page.