LLM API cost calculator
Compare homogeneous request groups with recorded billing conditions, or use the existing monthly usage estimate. Calculations are references; each quote keeps its native currency.
Example per call: read 500 characters, generate 300; 1 call(s) per task.
Adjust content lengths and assumptions
Include prompts, conversation history and attached context in the input. For multi-step tasks, use average content lengths per model call.
Characters per token is an adjustable planning assumption, not a measurement. Language, model and code affect it. Input and output scale together with tasks. Set extra per-request fees and reasoning usage separately in other assumptions.
Estimated monthly usage: 0.3M input, 0.18M output tokens, 600 calls.
Text-cost estimate for 600 tasks over 30 days per month.
Assumptions only change estimates; they never change the published prices.
Cheapest that fits
Loading quotes…
A specific model
Every current standard quote for this model, from official APIs and hosting providers. Ranked within each currency; currencies are never compared.
Estimate, not a bill: token and request charges only, in the quote’s own currency. Excludes tools, storage, search, taxes and platform fees. Different models tokenize the same task differently.