AI calculators
Token budgets, model costs, context windows, throughput and memory estimates for AI workloads.
Token Cost
Estimate an AI workload’s token cost using separate input and output token prices.
Context Window
Plan an AI context window by measuring prompt usage and reserving space for model output.
Inference Throughput
Measure AI inference throughput as generated tokens and completed requests per second.
Batch Processing Time
Estimate AI batch completion time from item count, average processing time and concurrency.
Model Memory
Estimate memory needed to store AI model parameters at a selected numeric precision.
Embedding Storage
Estimate raw and indexed storage for an AI embedding collection.
GPU Inference Cost
Estimate self-hosted AI inference cost from GPU price, token throughput, utilization and workload volume.