Prompt caching made Claude affordable for Instagram orders
A sushi chain with 7 locations takes about 90% of its orders through direct messages. was connected to those messages through the so it could answer customers automatically. The model needs access to the full menu, ingredients, calories, allergens, zones, opening hours, prep times, and current promotions for all 7 locations.
That is a large block of context, and normally it would be expensive to send and process again for every small customer message. Caching changed the cost. About 97% of messages reused the fixed information from cache instead of processing it again.
A cache read costs about one tenth of the normal input price, so the main full-price parts were only the customer’s short message and Claude’s reply. That made per-message Claude use practical for a real restaurant operation.
Key points
- The restaurant chain has 7 locations and gets about 90% of orders through direct messages.
- was connected through the to reply to customers.
- The model uses menu, ingredient, calorie, allergen, , hours, prep time, and promotion data.
- About 97% of messages reused the fixed information from cache.
- A cache read costs about one tenth of the normal input price.