Prompt Cost Calculator
Estimate AI prompt, completion and monthly token spend with retry and cache adjustments.
Calculate to see the token-cost split
Budget usage appears after calculation
Metrics appear after calculation
Your explanation appears here
Use your provider’s live price sheet for final billing, taxes, committed-use discounts or cached-token rules.
Your plan appears after calculation
Test different monthly runs and output length without changing the main result.
Calculate your baseline first
It multiplies input tokens by the input price and output tokens by the output price, scales by monthly runs, then adjusts for retries and cached-input discounts. All calculations run locally in your browser.
Many LLM APIs bill prompt/input tokens and completion/output tokens at different rates. Long completions can dominate spend even when prompts are short, so the calculator separates both sides.
The built-in tiers are editable planning presets, not live provider quotes. For production decisions, enter your provider’s current prices, cached-token rules, discounts and billing currency.
Prompt cost results are planning estimates generated locally in your browser. They do not include taxes, credits, minimum fees, rate-limit effects, committed-use discounts, currency conversion, provider-specific rounding, fine-tuning, embeddings, storage, moderation, retrieval or tool-call fees. VisionVix accepts no liability for decisions based on this output.