Product
ModelsSystems note 0.2

Small Models, Serious Research Economics

Compact model experiments focused on capability per parameter and visible API cost.

By North MLAugust 14, 20266 minute read
NORTH / RESEARCH RECORD030
Abstract

Compact model experiments focused on capability per parameter and visible API cost.

01

Capability per stage, not per product

A research product does not need one model to perform every operation. Query classification, extraction, deduplication, citation formatting, and final synthesis have different capability requirements.

North experiments with sub-billion-parameter models for bounded stages where latency, memory, and repeatability matter more than broad world knowledge. The parameter count is a constraint, not a quality claim.

02

Cost accounting that users can see

Total API cost is shaped by input length, retrieval volume, number of passes, model choice, and retries. A low token price can still produce an expensive workflow if the system repeatedly resends the same context.

Horizon budgets work by stage and preserves intermediate artifacts so a failed synthesis does not force retrieval and extraction to run again. The target is predictable research economics, not a universal promise of a particular price.

03

Where compact models fail

Small models are less forgiving when instructions are ambiguous, domains shift, or the task requires long-range synthesis. Routing must detect those cases and escalate rather than forcing a compact model to imitate capability it does not have.

Evaluation therefore includes refusal quality, escalation accuracy, and sensitivity to prompt variation. Cheap failure is still failure; efficiency only matters when the result remains useful.

Continue exploring North ML.

Return to ProductOpen Horizon ↗