Should I subtract the CachedInputTokens with InputTokens when I receive the 'Usage' object back from OpenAI response?

Im trying to calculate how much the response costs in total.

I get back values:

• Input: 1204
• Cached input: 1024
• Output: 12

OpenAI Pricing:

• Input: $0.150 / 1M tokens
• Cached input: $0.075 / 1M tokens
• Output: $0.600 / 1M tokens

I have tried using their official website to find the solution but didn't.

I was expecting Input to be lower (automatically subtracted with the cached input, so result would be 180). Not sure if I should subtract or not, when calculating everything.