For developers and product teams budgeting an AI feature before launch. You get input cost, output cost, cost per request and the total for your request volume, using editable per-million-token rates.
Build industry projects on ByteLabs and add verified proof of your skills to your public profile.
You enter
GPT-4o preset ($2.50 in, $10.00 out per 1M), 1,000 requests, 1,500 input and 500 output tokens each
The tool shows
Input $3.7500, output $5.0000, per request $0.0088, total $8.7500 (rates are editable estimates)
Cost is input tokens divided by 1 million times the input rate, plus output tokens divided by 1 million times the output rate, multiplied by the number of requests. Output tokens usually cost several times more than input.
They are indicative list prices dated in the tool and can go out of date. The rates in the tool are editable estimates, not live quotes. Check the provider pricing page and type the current rates into the rate boxes.
Shorten system prompts, cap max output tokens, cache repeated context where the provider supports it, and route simple requests to a smaller model. Re-run the calculator with each change to see the effect.
Yes. It is free, needs no sign-up and runs entirely in your browser, so what you type is not uploaded. You only sign in if you want to email a result to yourself or save it to your CareerByteCode profile.
