What will your API cost?
Turn a token price into a monthly bill. Every assumption is yours to change.
20M input tokens + 5M output tokens
Example: DeepSeek Flash, off-peak, no caching. Edit the prices. Excludes taxes, tools and retries.
How it works
Multiply request volume by the input and output cost of each request. Prices are USD per million tokens. The starting example uses 10,000 calls, 2,000 input tokens and 500 output tokens, at DeepSeek Flash off-peak rates of $0.15 and $0.60: a total of $6.00.
Formula: N × (I × Pi + O × Po) / 1,000,000. This excludes caching, taxes, additional tools and retries. To include retries, increase total requests. For caching, split hit and miss tokens as described in the token cache guide.
Example source: DeepSeek pricing, checked November 3, 2026. This is not a provider quote. Your inputs stay in your browser.
The cost of switching
Token price is only part of the comparison. Include output length, acceptance rate and integration time. Read how to estimate a DeepSeek migration.