Not Diamond
Type: app · Vendor: Not Diamond · Language: API · License: proprietary · Status: active · Status in practice: mature
Commercial intelligent model-routing service that predicts the best-performing model per query and dispatches automatically across configured endpoints.
Description. Not Diamond is a hosted model router for LLM applications. Customers register the set of candidate models they want to consider and call Not Diamond's API with a query; a meta-model that learns when to call each LLM predicts the best target and the request is dispatched there. The product positions itself around quality maximisation and cost reduction — simple queries are routed to cheap models, complex queries to frontier models — without the customer hand-coding a routing policy. A pre-trained router gets users started quickly; custom routers can be trained on the customer's own preference data.
Agent loop shape. Hosted decision API. The application sends each prompt to Not Diamond with the configured candidate model list; Not Diamond analyses the input and predicts which model will provide the highest quality response at the lowest cost for that specific query, then (optionally) executes the call. Routing is stateless per request; configuration lives in the Not Diamond dashboard / API call parameters, and learned preference data drives the meta-model behind the routing decision.
Primary use cases
- automatic best-model selection per query
- cost reduction over single-model deployments by routing simple queries to cheap models
- quality-maximising routing across heterogeneous models
- managed routing without authoring rules
- custom router training on customer preference data
Key concepts
- Meta-model router → multi-model-routing (docs) — A learned model that decides which underlying LLM to call for each query, combining the candidate models into a single routed endpoint.
- Per-query analysis → complexity-based-routing (docs) — Router analyses each input and predicts the highest-quality, lowest-cost model for that specific query.
- Pre-trained and custom routers (docs) — Customers can start with Not Diamond's pre-trained router or train a custom router on their own preference data.
- Cost-vs-quality tradeoff routing → complexity-based-routing (docs) — Routing policy explicitly trades cost against quality: simple queries to cheap models, complex queries to frontier models.
Patterns this app implements —
- ★★Multi-Model Routing
The product is a router across a configured set of models — that is its single function.
- ★Complexity-Based Routing
Routing decision is driven by a learned model that predicts which model will perform best on a given query; the docs explicitly frame the policy as simple-vs-complex query routing.