Amazon Fraud Detector endpoints and quotas
The following are the service endpoints and service quotas for this service. To connect programmatically to an AWS service, you use an endpoint. In addition to the standard AWS endpoints, some AWS services offer FIPS endpoints in selected Regions. For more information, see AWS service endpoints. Service quotas, also referred to as limits, are the maximum number of service resources or operations for your AWS account. For more information, see AWS service quotas.
Service endpoints
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (Ohio) | us-east-2 | frauddetector.us-east-2.amazonaws.com | HTTPS |
| US East (N. Virginia) | us-east-1 | frauddetector.us-east-1.amazonaws.com | HTTPS |
| US West (Oregon) | us-west-2 | frauddetector.us-west-2.amazonaws.com | HTTPS |
| Asia Pacific (Singapore) | ap-southeast-1 | frauddetector.ap-southeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 | frauddetector.ap-southeast-2.amazonaws.com | HTTPS |
| Europe (Ireland) | eu-west-1 | frauddetector.eu-west-1.amazonaws.com | HTTPS |
Service quotas
| Name | Default | Adjustable | Description |
|---|---|---|---|
| Concurrent training jobs per model | Each supported Region: 1 | No | Maximum number of concurrent training jobs per model. |
| Deployed model versions | Each supported Region: 5 | No | Maximum number of deployed model versions per account. |
| Detectors per account | Each supported Region: 100 | No | Maximum number of detectors per account. |
| EntityType per account | Each supported Region: 100 | No | Maximum number of EntityType per account |
| EventType per account | Each supported Region: 100 | No | Maximum number of EventType per account |
| Labels per account | Each supported Region: 100 | No | Maximum number of labels per account |
| Lists per account | Each supported Region: 100 | No | Maximum number of lists per account. |
| Models including external models per detector version | Each supported Region: 10 | No | Maximum number of models including external models per detector version. |
| Models per account | Each supported Region: 50 | No | Maximum number of models per account. |
| Outcomes per account | Each supported Region: 5,000 | No | Maximum number of outcomes per account. |
| Rate of GetPrediction requests | Each supported Region: 200 |
Yes |
Maximum number of GetPrediction API calls that you can make per second. |
| Rules per account | Each supported Region: 5,000 | No | Maximum number of rules per account. |
| Size of GetPrediction requests | Each supported Region: 256 Kilobytes | No | Maximum size of payload per GetPrediction API call. |
| Total concurrent Event Type statistics update operations | Each supported Region: 1 |
Yes |
Maximum total number of concurrent Event Type statistics update operations per account. |
| Total concurrent training jobs | Each supported Region: 3 | No | Maximum total number of concurrent training jobs per account. |
| Training data size | Each supported Region: 5 Gigabytes | No | Maximum size of Fraud Detector model training data. |
| Variables per account | Each supported Region: 5,000 | No | Maximum number of variables per account. |
| Versions per detector | Each supported Region: 100 | No | Maximum number of draft versions per detector. |
| Versions per model | Each supported Region: 200 | No | Maximum number of versions per model. |
For more information, see Quotas in the Amazon Fraud Detector User Guide.
