- Set the workload
Enter requested clips and any other volume assumptions that define the period or batch.
- Add usage assumptions
Complete the remaining usage fields, keeping token, duration, or size units consistent with their labels.
- Enter current rates
Use the current prices for the exact model, endpoint, quality, and processing tier you plan to use.
- Review the estimate
Read the main result and the supporting breakdown to see the largest cost or capacity driver.
- Test another scenario
Change one assumption at a time or select Reset to restore the default example values.
OpenAI Video Calculator
The OpenAI Video Calculator estimates generation spend and output storage from clip count, duration, per-second price, retries, and file bitrate. It works with any video model whose price can be expressed per generated second.
Creators and product teams can use it to compare short drafts with longer final renders, budget batch production, and estimate the storage impact of retained outputs. Audio, upscaling, editing, or other add-on charges should be entered through an adjusted rate or modeled separately.
Calculation inputs
clips
seconds
USD
%
%
Mbps
Result
—
Estimated result
Billed generation time—
Expected usable clips—
Approximate storage—
Spend per usable clip—
Billed seconds = Clips × Seconds per clip × (1 + retry overhead ÷ 100). Spend = Billed seconds × price per second. Storage GB ≈ Usable clips × seconds × Mbps ÷ 8 ÷ 1,024.
The calculator applies the entered values directly and displays rounded results for planning.
What the result means
The result estimates generation charges for all requested and retried video seconds.
Use the rate and supported resolution from the current model documentation; encoding bitrate is only a storage assumption.
Given: Example assumptions
Calculation: For 100 ten-second clips at $0.10 per second with 10% retry overhead, billed time is 1,100 seconds and estimated spend is $110. At an 80% usable rate and 8 Mbps, 80 retained clips require about 0.78 GB.
Result: The displayed result follows the same formula and rounding logic.
Does resolution affect the price?
It can. Enter the per-second rate for the exact model, resolution, and tier you plan to use.
What should retry overhead include?
Include reruns caused by technical failures and outputs that must be regenerated before review.
Does the storage formula include audio?
The bitrate field can represent the combined encoded stream. Add audio bitrate if your video bitrate figure excludes it.
Can I model clips with different lengths?
Run separate estimates for each duration group and add the totals.
Is usable clip rate the API success rate?
Not necessarily. It is the percentage you expect to keep after quality and policy review.