How is LLM API cost calculated?
The calculator multiplies monthly input and output token volume by each model's per-1M-token prices. Cache hit ratio and batch discount are applied only when you enter them.
LLM API cost estimate, monthly token math
Calculate GPT, Claude, Gemini, and other model API costs with monthly requests, input/output tokens, cache hit ratio, batch discounts, and context limits.
Cost estimateLLM Table
Tune volumes, cache, and batch discount—totals update instantly with the same teal field language as the home quick estimate.
Total monthly cost
OpenRouter$250.00
Results
Input cost
$100.00
Cached input
$0.00
Output cost
$150.00
Per request
$0.002500
Per 1K requests
$2.50
Per 100K requests
$250.00
Per 1M requests
$2,500.00
Monthly tokens
130,000,000
Cheaper alternatives
This is an estimate, not a real-world result.
All prices, model data, token counts, and calculator outputs are example estimates only. Accuracy, completeness, timeliness, or fitness is not guaranteed; LLMRateRadar accepts no responsibility for decisions made from these results.
FAQ
Cost calculation notes
Are missing prices treated as free?
No. If a model is missing input or output pricing, LLMRateRadar marks that scenario as unavailable instead of treating unknown prices as zero.
Why do direct API and OpenRouter prices differ?
The same underlying model can have different prices by route. LLMRateRadar keeps direct provider records and aggregator route records separate.
Should I verify prices before production use?
Yes. Prices can change quickly, so production decisions should always be checked against the official provider pricing page.
