8 Services from llm-cost-calc.x402tookit.com

Calculates sustainable requests per minute, job duration, and concurrency needed given RPM and TPM provider limits and tokens per request.

Calculates prompt-caching cost savings for a shared prefix: costs with and without caching, break-even request count, and percent saved.

Compares realtime vs. batch API cost for an LLM workload given token counts, prices, and a discount fraction, and returns how much money is saved by using batch mode.

Calculates the cost of LLM API calls given input and output token counts and per-million-token prices, returning per-request and total cost breakdowns.

Ranks 2–20 LLM models by total cost for a given workload using caller-supplied prices, and flags models whose context window is too small.

Checks whether a prompt fits within a model's context window (with output reserve and safety headroom) and estimates how many additional chat turns remain.

Forecasts monthly and yearly LLM API spend from daily request volume, token counts, and per-million-token prices, with optional growth rate and per-user cost breakdown.

Estimates the number of LLM tokens in a text string (low/mid/high range) from character and word counts, without running a full tokenizer.