Free calculator · No account required
LLM cost calculator
Model token spend across calls, retries and caching using the rates you supply.
Your inputs stay in this browser tab. Saving to this device is optional.
Draft name and device saving
Current draft matches the last save or initial state.
Complete your inputs
Calculated result
Awaiting complete inputsEnter your values to see the result, or choose Try an example to explore a completed worksheet.
How this result is calculated
Billable calls = monthly tasks × base calls per task × (1 + extra-call percentage). Input cost splits tokens between ordinary and cached rates, then adds output cost. All prices must use the same currency and per-million-token unit. Per-task cost includes the allocated fixed monthly amount.
Keep your work
Resume later
Save an editable JSON draft. Use Open draft to bring it back into this tool.
Share a report
Reports include your inputs, assumptions and any unresolved checks.
Read the complete report
# LLM cost calculator Tool defaults; replace with your settings before operational use. ## Review issues - User tasks per month: enter a whole number from 1 to 1000000000000. - Input tokens per call: enter a whole number from 0 to 1000000000000. - Billable output tokens per call: enter a whole number from 0 to 1000000000000. - Input price per million tokens: enter a number from 0 to 1000000000000. - Output price per million tokens: enter a number from 0 to 1000000000000. ## Inputs Model and rate source: Not entered Price currency (three-letter code): USD User tasks per month: Not entered Base model calls per task: 1 Extra calls from retries (%): 0 Input tokens per call: Not entered Billable output tokens per call: Not entered Input tokens billed at cached rate (%): 0 Input price per million tokens: Not entered Cached input price per million tokens: Not entered Output price per million tokens: Not entered Other fixed monthly costs: 0 ## Method Billable calls = monthly tasks × base calls per task × (1 + extra-call percentage). Input cost splits tokens between ordinary and cached rates, then adds output cost. All prices must use the same currency and per-million-token unit. Per-task cost includes the allocated fixed monthly amount. Use current billing documentation and measured token usage. Include billable reasoning tokens in output where applicable. Tool execution, search, storage, images, audio, taxes, cache-write fees and tiered discounts must be accounted for separately. This is an estimate; it does not query an account or provider. https://aiopssre.com/llm-cost-calculator/
How it works
Billable calls = monthly tasks × base calls per task × (1 + extra-call percentage). Input cost splits tokens between ordinary and cached rates, then adds output cost. All prices must use the same currency and per-million-token unit. Per-task cost includes the allocated fixed monthly amount.
Follow the example
The fictional example has 33,000 billable calls. Each costs $0.00725 in tokens, making token spend $239.25. Adding $20 in fixed costs gives $259.25 per month, or $0.025925 per user task. These are illustrative rates, not a provider price quote.
What to account for
Use current billing documentation and measured token usage. Include billable reasoning tokens in output where applicable. Tool execution, search, storage, images, audio, taxes, cache-write fees and tiered discounts must be accounted for separately. This is an estimate; it does not query an account or provider.