A quota restricts how much of a shared Google Cloud resource your Google Cloud project can use, including hardware, software, and network components. Therefore, quotas are a part of a system that does the following:
- Monitors your use or consumption of Google Cloud products and services.
- Restricts your consumption of those resources, for reasons that include ensuring fairness and reducing spikes in usage.
- Maintains configurations that automatically enforce prescribed restrictions.
- Provides a means to request or make changes to the quota.
In most cases, when a quota is exceeded, the system immediately blocks access to the relevant Google resource, and the task that you're trying to perform fails. In most cases, quotas apply to each Google Cloud project and are shared across all applications and IP addresses that use that Google Cloud project.
Total requests quotas
The following quotas apply to AML AI requests:
Quota | Value |
---|---|
Requests per second per project per region | 100 |
Requests per second per organization per region | 100 |
Number of parties used in requests to
projects.locations.instances.engineConfigs.create
per day per project |
55,000,000 |
Number of parties used in requests to
projects.locations.instances.engineConfigs.create
per day per organization |
55,000,000 |
Number of parties used in requests to
projects.locations.instances.models.create
per day per project |
55,000,000 |
Number of parties used in requests to
projects.locations.instances.models.create
per day per organization |
55,000,000 |
Number of parties used in requests to
projects.locations.instances.backtestResults.create
multiplied by the number of backtest periods per day per project |
55,000,000 |
Number of parties used in requests to
projects.locations.instances.backtestResults.create
multiplied by the number of backtest periods per day per organization |
55,000,000 |
Number of registered parties used in requests to
projects.locations.instances.predictionResults.create
multiplied by the number of prediction periods per day per project |
55,000,000 |
Number of registered parties used in requests to
projects.locations.instances.predictionResults.create
multiplied by the number of prediction periods per day per organization |
55,000,000 |
Concurrent request quotas
The following quotas apply to concurrent requests:
Quota | Value |
---|---|
Tuning requests per project per region | 1 |
Training requests per project per region | 5 |
Inference requests (
projects.locations.instances.backtestResults.create
and
projects.locations.instances.predictionResults.create
combined) per project per region |
5 |
Collection size quotas
The following quotas apply to AML AI collections. These quotas don't reset over time and instead are released when you delete a resource.
Quota | Value |
---|---|
Instances per project per region | 10 |
Datasets per project per region | 1000 |
EngineConfigs per project per region | 1000 |
Models per project per region | 1000 |
Registered parties allocation limit
Quota | Value |
---|---|
Registered parties per project per region | 20,000,000 |
Request a quota increase
AML AI does not currently support increasing quotas via the Google Cloud console, to request a quota increase, please reach out to support.
To decrease most quotas, use the Google Cloud console. For more information, see Requesting a higher quota.
Set up quota alerts
You can set up quota alerts to get notifications when quota usage reaches a defined threshold. For more information, see Set up quota usage alerts in the Quotas page.