AI planning
Interactive tools with transparent methods. Change the inputs, check the example and use the result with its assumptions.
AI Token Cost Calculator
Token cost equals input tokens × input rate ÷ one million plus output tokens × output rate ÷ one million. Enter the rates for your actual provider and processing tier.
Cached Input Cost Calculator
Mixed input cost equals cached tokens at the cache-read rate plus remaining tokens at the uncached rate. A cache hit fraction is an input assumption, not a guaranteed provider behavior.
Context Window Budget Calculator
Remaining context equals the supplied context limit minus instruction tokens, history tokens and output reserve. Count all relevant prompt material using your provider’s tokenization rules.
AI Request Budget Calculator
Affordable whole requests equal budget divided by estimated per-request token cost, rounded down. The calculation assumes the same average input and output usage for each request.
Token Generation Time Calculator
For positive output length, estimated time equals first-token latency plus the remaining token count divided by the generation rate. Zero requested tokens gives zero modeled generation time.
Embedding Vector Storage Calculator
Raw embedding storage equals vector count multiplied by dimensions and bytes per component. One thousand 1,536-dimensional vectors at four bytes per component require 6,144,000 bytes before indexing overhead.
AI token cost: volume and price sensitivity table
Compare hypothetical costs at several rates per million tokens. Prices are editable planning assumptions, not current provider prices. Input and output tokens may have different rates.
AI context budget: reserve space before adding input
Reserve output capacity before filling a context window with input. The table allocates 10% of each example window to output and shows the remaining input ceiling.