Model tiers
Providers sell a ladder of models at very different prices. Higher rungs cost more per token, tend to be slower and tend to do better on hard work. The names change often, so check the current list rather than remembering one.
Using the top rung to rename a variable is waste, and the cheapest rung on a hard task can cost more in retries than getting it right once. Judge a tier by its cost per finished task, on your tasks.
Say it to your agent
“Use claude-haiku-5-5 for the bulk file summaries and claude-opus-5-5 for the plan. Log cost and pass or fail per task for this week, and show me the table before we change the split.”