Tokens per BIN — cache read / cache write / input / output
OutputInputCache writeCache read
Model Breakdown
Token Split
Date
Model
Input
Output
Cache Read
Cache Write
API Calls
Cost (USD)
Costs are estimated from token counts using published Bedrock on-demand rates for each model.
The four token types — input, output, cache read, and cache write — are priced separately at the per-million-token rates below.
A request's cost is the sum of (tokens ÷ 1,000,000) × rate across all four types in USD.