Glossary / AI Fundamentals

Model Tier

A rough level of model capability, speed, and cost, used to match the model to the job.

Updated July 2, 2026

A model tier is a rough level of capability, speed, and cost. Higher tier usually means better judgment and harder reasoning plus more cost and waiting, so the skill is matching the model to the job. You’ll feel tiers inside Claude Code: a stronger model thinks longer, a lighter one answers fast and misses more edge cases.

Picture choosing a vehicle for a delivery. A box truck carries a couch across town, but it’s slow and overkill for a one-page envelope. A bike courier is cheaper and faster for the envelope and wrong for the couch.

Why you care

Start heavy, then step down. When you’re learning a workflow, building a first version, or reasoning through a mess, use the strongest model you have; we default there until limits or cost bite. Once the work is understood and documented as a clear skill or template, a faster, cheaper tier can often repeat it. That’s the pattern we teach: the stronger model figures out the job, the cheaper model repeats it. Names and rankings change; the matching problem stays. Stop sending the box truck for every envelope.