RESOURCES
To protect our API against abuse and ensure fair access, we have set limits on the number of generations you can create. Each organization has a set of limits, which apply per organization, not per API key.
The concurrency limit is the maximum number of tasks that can run simultaneously. If you submit more tasks than allowed, your excess tasks will be in queueing status, indicating they are stored but not yet processed. Throttled tasks are enqueued roughly in submission order.
In rare cases, you may experience lower than maximum concurrency depending on system load. If you are interested in guaranteed (minimum) concurrency, please contact us using the limits exception form in the usage page of the developer portal.
To help you better understand the concurrency limit policy, here is an example:
Assume you want to generate 1000 videos and you have a concurrency limit of 5:
- You can submit all 1000 video request tasks at the same time.
- Vidu API handles the queueing logic and starts executing them in rapid fashion 5-at-a-time, in sequential order based on creation time.
- The first 5 videos finish in 30 seconds and the 6th to 10th videos begin generating. They finish in 30 additional seconds.
- All 1000 videos are complete within 100 minutes (30 seconds x 1000 videos / 5 concurrency).
Each organization can use up to 5 concurrent tasks. This means you can generate up to 5 tasks simultaneously.
For custom tier information, higher limits, or guaranteed concurrency, file an exception request from the usage page when logged in to the developer portal. These and other benefits you can contact:
platform@vidu.studioIn addition to higher rate limits, enterprise customers receive:
- Faster support via Discord (or email) channels
- Earliest access to new features
- Direct access to provide product feedback and request features
- Implementation and usage tips
- Custom payment terms