LLM API Cost Calculator
Turn token prices into a monthly budget before your feature hits production.
Estimate your workload
Change the assumptions on the left; read the modeled result on the right.
How to read this estimate
What this calculator is for
Use this when you know roughly how large each model call is and how many calls your product will make. It is the fastest way to translate a provider pricing table into a monthly operating estimate.
How to read the result
Estimated monthly API cost includes modeled input and output text tokens. Per request divides that total by request volume; Annual run rate multiplies monthly spend by 12. Input and output rates show the currently selected model’s applicable tier.
The math
The monthly estimate multiplies your token cost per request by the number of requests.
Pricing sources
Rates use the published TokenCOGS pricing registry and its September 16, 2026 fallback snapshot. Live values may differ; see methodology and source limitations before procurement.
Planning limitations
Actual invoices can differ because providers may apply long-context pricing, caching rules, batch rates, tool-call fees, regional processing, negotiated contracts, taxes, or future pricing changes. Treat the output as a planning estimate.
Use it to create scenarios and catch order-of-magnitude mistakes. Before committing spend, verify the selected model's live provider pricing and compare the estimate with actual usage telemetry.
Do these totals include provider tool or infrastructure charges?
No. The core estimate covers billed text input/output tokens. Hosted tools, regional surcharges and infrastructure are not included.
Why are input and output priced separately?
Most providers publish distinct rates for tokens sent to the model and tokens generated by the model, so both parts must be modeled independently.