How Switch Trust calculates cost
Each model has a price for each kind of token, in US dollars per million tokens (/ MTok):- Input: Tokens sent to the model, not counting tokens read from the cache
- Output: Tokens the model generates
- Cache read: Input tokens served from the provider prompt cache
- Cache write: Input tokens written to the provider prompt cache
Read the pricing list
Models are grouped by provider, such as Anthropic, and listed alphabetically. Each row shows the model name, when its prices date from (Prices as of), and its Input, Output, Cache read, and Cache write prices. The list includes:- Models with a list price. Switch Trust ships with list prices for widely used models from major providers, whether or not your agents call them. These rows have no badge.
- Models with a negotiated rate. You’ve set your own prices for these. They’re marked Negotiated, and each changed price shows the list price it replaces, struck through.
- Models with no price. Your agents call these, but Switch Trust has no list price for them. They’re marked Unpriced and show a dash in place of each price.
Set a negotiated rate
Use a negotiated rate when you pay a provider something other than its list price, or to price a model that’s marked Unpriced.1
Open the model for editing
Find the model in the list. Select Edit, or Set pricing if the model is marked
Unpriced.
2
Enter your prices
Enter a price in each of Input $ / MTok, Output $ / MTok, Cache Read $ / MTok,
and Cache Write $ / MTok. Every field is required. Enter
0 for a kind of token your
provider doesn’t charge for. Prices can’t be negative and are rounded to four decimal places.3
Save the rate
Select Save.
Go back to the list price
On a model marked Negotiated, select Reset to list price. The negotiated rate is removed immediately, with no confirmation, and every cost figure goes back to using the list price. A model that had no list price goes back to Unpriced, and its usage counts as $0 again.Where your prices are used
Every cost figure in Switch Trust uses the prices on this page:- Total AI spend and Spending cap summary on the Agents page
- The Cost (MTD), $/session (MTD), and Cap usage (MTD) columns in the agents table
- Cost by month, $ per session, and Burn rate on the agent Overview tab
- The cost of each session on the agent Sessions tab
The estimated savings on the agent Improvements
tab are worked out from list prices, not from your negotiated rates. They can differ from what
your own rates would give.

