What it costs depends mostly on how much of the counter the system is going to own. Answering routine parts calls and drafting a ticket (phone rings, stock check, a price, a record in the yard software) is a narrower job than a system that also matches interchange, pulls a shipping quote, and writes the exchange back into inventory. A single workflow costs less to build than a connected system covering inquiries, inventory, interchange, and shipping together. A customer-facing quote tool with payments and more than one yard location is a different scale of build again.
The other driver is whether you want it built and handed off, or built and operated. A one-time build is cheaper up front but leaves you to notice when it starts quoting stale prices, missing a new interchange match, or failing quietly on a busy Saturday. We run the systems we build: watching for failures, updating it as inventory or pricing changes, and stepping in when something needs a person's judgment. That ongoing operation is part of what gets quoted, not something added later.
Look at how much staff time goes into answering the same handful of question types, and how much of that can honestly be handed to a system versus needs a person's eyes on the part. If most incoming calls are "do you have this part" and "does this fit," that is a strong candidate. If most calls involve walking the yard to check condition or negotiating a price, less of the job can be automated, and the engagement should be scoped that way. Tell us which of your calls are actually repetitive and we will tell you what that scope looks like to build and run.