LLM API Cost Calculator
Estimate what an LLM API costs per request and per month. Pick a model (prices preset and editable), then enter tokens and volume.
How it works & a note on prices
Cost = (input tokens × input price + output tokens × output price) ÷ 1,000,000, times your monthly request volume. Claude model IDs and prices are preset (Opus 4.8 $5/$25, Fable 5 $10/$50, Sonnet 4.6 $3/$15, Haiku 4.5 $1/$5 per million input/output tokens) and editable — for OpenAI, Gemini, or others, choose "Other" and enter their published per-million-token rates. The Batch API runs non-urgent requests at about 50% of standard price; prompt caching serves a repeated input prefix at ~10% of the input price (a cache write costs ~1.25× once). Always confirm current pricing with the provider.
Frequently asked questions
What's the cheapest Claude model?
Claude Haiku 4.5 at $1 input / $5 output per million tokens, for simple high-volume tasks. Opus 4.8 ($5/$25) is the most capable; Sonnet 4.6 ($3/$15) balances cost and capability.
How do batch and caching cut cost?
The Batch API processes non-urgent requests at about half price. Prompt caching reuses a large fixed prefix across requests at ~10% of the input price — a big saving when the same context repeats every call.