Pick model

Goal: each task runs on the cheapest model that does it well enough. The strongest model on everything wastes money. The cheapest model on everything wastes time on bad output.

1. Find the calls

Search the code and config for model use: model IDs, provider SDK calls, agent and subagent definitions, cron jobs and bots. For each call, write down:

• Task (what it does, in five words).
• Current model.
• Rough volume (per day or per run) and size (short prompt or long context).
• How bad a weak answer is: low (draft, sorted later), medium (user sees it), high (money, security, code that ships, public posts).

2. Get current prices

With the explainx.ai MCP server: call compare_model_prices for the candidate models, and search_ai_directory or get_ai_directory_entry for model details. Prices change often. Never use prices from memory. Without the server, use the providers' pricing pages and give the date you read them.

Router prices can differ from direct provider prices. Say which one you used.

3. Match model to task