AWS Amazon Braket Service Limits
101 quotas for Amazon Braket. 74 can be increased.
| Quota | Default | Status |
|---|---|---|
Maximum number of instances of ml.g6.24xlarge for jobs Maximum number of instances of ml.g6.24xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.g5.48xlarge for jobs Maximum number of instances of ml.g5.48xlarge for jobs capacity | 0 count | Fixed |
Number of concurrent DM1 tasks Number of concurrent DM1 tasks compute | 100 count | Fixed |
Maximum number of instances of ml.p2.16xlarge for jobs Maximum number of instances of ml.p2.16xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g5.8xlarge for jobs Maximum number of instances of ml.g5.8xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.c5.9xlarge for jobs Maximum number of instances of ml.c5.9xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.g6e.12xlarge for jobs Maximum number of instances of ml.g6e.12xlarge for jobs capacity | 1 count | Adjustable |
Rate of GetDevice requests Rate of GetDevice requests throughput | 5 count | Adjustable |
Number of concurrent SV1 tasks Number of concurrent SV1 tasks compute | 100 count | Fixed |
Maximum number of instances of ml.t3.large for jobs Maximum number of instances of ml.t3.large for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g6e.xlarge for jobs Maximum number of instances of ml.g6e.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g4dn.16xlarge for jobs Maximum number of instances of ml.g4dn.16xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.t3.xlarge for jobs Maximum number of instances of ml.t3.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5.2xlarge for jobs Maximum number of instances of ml.c5.2xlarge for jobs capacity | 5 count | Adjustable |
Rate of UpdateSpendingLimit requests Rate of UpdateSpendingLimit requests throughput | 2 count | Adjustable |
Rate of GetJob requests Rate of GetJob requests throughput | 5 count | Adjustable |
Maximum number of instances of ml.g6e.24xlarge for jobs Maximum number of instances of ml.g6e.24xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.p3.2xlarge for jobs Maximum number of instances of ml.p3.2xlarge for jobs capacity | 0 count | Adjustable |
Rate of SearchSpendingLimits requests Rate of SearchSpendingLimits requests throughput | 5 count | Adjustable |
Maximum number of instances of ml.p4d.24xlarge for jobs Maximum number of instances of ml.p4d.24xlarge for jobs capacity | 0 count | Fixed |
Rate of GetQuantumTask requests Rate of GetQuantumTask requests throughput | 100 count | Adjustable |
Rate of CancelJob requests Rate of CancelJob requests throughput | 2 count | Adjustable |
Maximum number of instances of ml.m5.2xlarge for jobs Maximum number of instances of ml.m5.2xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.m4.2xlarge for jobs Maximum number of instances of ml.m4.2xlarge for jobs capacity | 5 count | Adjustable |
Rate of API requests Rate of API requests throughput | 140 count | Adjustable |
Maximum number of instances of ml.g6.2xlarge for jobs Maximum number of instances of ml.g6.2xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.m5.xlarge for jobs Maximum number of instances of ml.m5.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g5.2xlarge for jobs Maximum number of instances of ml.g5.2xlarge for jobs capacity | 0 count | Fixed |
Rate of CreateQuantumTask requests Rate of CreateQuantumTask requests throughput | 20 count | Adjustable |
Maximum number of instances of ml.m4.10xlarge for jobs Maximum number of instances of ml.m4.10xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.c4.4xlarge for jobs Maximum number of instances of ml.c4.4xlarge for jobs capacity | 5 count | Adjustable |
Number of concurrent TN1 tasks Number of concurrent TN1 tasks compute | 10 count | Adjustable |
Rate of SearchJobs requests Rate of SearchJobs requests throughput | 5 count | Adjustable |
Maximum number of instances of ml.m4.xlarge for jobs Maximum number of instances of ml.m4.xlarge for jobs capacity | 5 count | Adjustable |
Rate of CreateJob requests Rate of CreateJob requests throughput | 1 count | Adjustable |
Maximum number of instances of ml.g6.xlarge for jobs Maximum number of instances of ml.g6.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5n.9xlarge for jobs Maximum number of instances of ml.c5n.9xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g4dn.xlarge for jobs Maximum number of instances of ml.g4dn.xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.c5.xlarge for jobs Maximum number of instances of ml.c5.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5n.18xlarge for jobs Maximum number of instances of ml.c5n.18xlarge for jobs capacity | 0 count | Adjustable |
Burst rate of SearchSpendingLimits requests Burst rate of SearchSpendingLimits requests throughput | 50 count | Fixed |
Maximum number of instances of ml.g6e.16xlarge for jobs Maximum number of instances of ml.g6e.16xlarge for jobs capacity | 1 count | Adjustable |
Rate of SearchDevices requests Rate of SearchDevices requests throughput | 5 count | Adjustable |
Maximum number of instances of ml.p3.8xlarge for jobs Maximum number of instances of ml.p3.8xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g6e.2xlarge for jobs Maximum number of instances of ml.g6e.2xlarge for jobs capacity | 5 count | Adjustable |
Rate of SearchQuantumTasks requests Rate of SearchQuantumTasks requests throughput | 5 count | Adjustable |
Rate of CreateSpendingLimit requests Rate of CreateSpendingLimit requests throughput | 2 count | Adjustable |
Maximum number of instances of ml.g4dn.4xlarge for jobs Maximum number of instances of ml.g4dn.4xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g6.16xlarge for jobs Maximum number of instances of ml.g6.16xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5n.4xlarge for jobs Maximum number of instances of ml.c5n.4xlarge for jobs capacity | 0 count | Adjustable |
Burst rate of DeleteSpendingLimit requests Burst rate of DeleteSpendingLimit requests throughput | 5 count | Fixed |
Maximum number of instances of ml.c4.8xlarge for jobs Maximum number of instances of ml.c4.8xlarge for jobs capacity | 5 count | Adjustable |
Burst rate of UpdateSpendingLimit requests Burst rate of UpdateSpendingLimit requests throughput | 5 count | Fixed |
Rate of DeleteSpendingLimit requests Rate of DeleteSpendingLimit requests throughput | 2 count | Adjustable |
Maximum number of instances of ml.g6.12xlarge for jobs Maximum number of instances of ml.g6.12xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.m5.4xlarge for jobs Maximum number of instances of ml.m5.4xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.m4.4xlarge for jobs Maximum number of instances of ml.m4.4xlarge for jobs capacity | 2 count | Adjustable |
Maximum number of instances of ml.g6.48xlarge for jobs Maximum number of instances of ml.g6.48xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.m5.24xlarge for jobs Maximum number of instances of ml.m5.24xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g6e.8xlarge for jobs Maximum number of instances of ml.g6e.8xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g4dn.8xlarge for jobs Maximum number of instances of ml.g4dn.8xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g5.xlarge for jobs Maximum number of instances of ml.g5.xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.p3.16xlarge for jobs Maximum number of instances of ml.p3.16xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.g4dn.2xlarge for jobs Maximum number of instances of ml.g4dn.2xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.c5n.xlarge for jobs Maximum number of instances of ml.c5n.xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.p2.xlarge for jobs Maximum number of instances of ml.p2.xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.c4.xlarge for jobs Maximum number of instances of ml.c4.xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.p3dn.24xlarge for jobs Maximum number of instances of ml.p3dn.24xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.g5.4xlarge for jobs Maximum number of instances of ml.g5.4xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.p2.8xlarge for jobs Maximum number of instances of ml.p2.8xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.m5.12xlarge for jobs Maximum number of instances of ml.m5.12xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.c5.4xlarge for jobs Maximum number of instances of ml.c5.4xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.g6.4xlarge for jobs Maximum number of instances of ml.g6.4xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g5.12xlarge for jobs Maximum number of instances of ml.g5.12xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.g5.24xlarge for jobs Maximum number of instances of ml.g5.24xlarge for jobs capacity | 0 count | Fixed |
Maximum number of instances of ml.g6e.4xlarge for jobs Maximum number of instances of ml.g6e.4xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g6e.48xlarge for jobs Maximum number of instances of ml.g6e.48xlarge for jobs capacity | 1 count | Adjustable |
Maximum number of instances of ml.g5.16xlarge for jobs Maximum number of instances of ml.g5.16xlarge for jobs capacity | 0 count | Fixed |
Rate of CancelQuantumTask requests Rate of CancelQuantumTask requests throughput | 2 count | Adjustable |
Maximum number of instances of ml.g4dn.12xlarge for jobs Maximum number of instances of ml.g4dn.12xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.m5.large for jobs Maximum number of instances of ml.m5.large for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.g6.8xlarge for jobs Maximum number of instances of ml.g6.8xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5.18xlarge for jobs Maximum number of instances of ml.c5.18xlarge for jobs capacity | 0 count | Adjustable |
Maximum number of instances of ml.t3.2xlarge for jobs Maximum number of instances of ml.t3.2xlarge for jobs capacity | 5 count | Adjustable |
Maximum number of instances of ml.c5n.2xlarge for jobs Maximum number of instances of ml.c5n.2xlarge for jobs capacity | 0 count | Adjustable |
Burst rate of CreateSpendingLimit requests Burst rate of CreateSpendingLimit requests throughput | 5 count | Fixed |
Maximum number of instances of ml.c4.2xlarge for jobs Maximum number of instances of ml.c4.2xlarge for jobs capacity | 5 count | Adjustable |
Number of concurrent jobs Number of concurrent jobs compute | 3 count | Adjustable |
Maximum number of instances of ml.m4.16xlarge for jobs Maximum number of instances of ml.m4.16xlarge for jobs capacity | 0 count | Adjustable |
Burst rate of GetJob requests Burst rate of GetJob requests throughput | 25 count | Fixed |
Burst rate of API requests Burst rate of API requests throughput | 600 count | Fixed |
Burst rate of SearchQuantumTasks requests Burst rate of SearchQuantumTasks requests throughput | 50 count | Fixed |
Burst rate of CancelQuantumTask requests Burst rate of CancelQuantumTask requests throughput | 20 count | Fixed |
Burst rate of GetDevice requests Burst rate of GetDevice requests throughput | 50 count | Fixed |
Burst rate of CreateJob requests Burst rate of CreateJob requests throughput | 5 count | Fixed |
Burst rate of SearchDevices requests Burst rate of SearchDevices requests throughput | 50 count | Fixed |
Burst rate of GetQuantumTask requests Burst rate of GetQuantumTask requests throughput | 500 count | Fixed |
Burst rate of CreateQuantumTask requests Burst rate of CreateQuantumTask requests throughput | 40 count | Fixed |
Burst rate of SearchJobs requests Burst rate of SearchJobs requests throughput | 50 count | Fixed |
Maximum allowed compute instances for a job Maximum allowed compute instances for a job compute | 1 count | Adjustable |
Burst rate of CancelJob requests Burst rate of CancelJob requests throughput | 5 count | Fixed |
How to Request a Quota Increase
- 1Open the AWS Service Quotas console.
- 2Select Amazon Braket from the service list.
- 3Find the quota and click "Request increase".
- 4Enter the desired value and submit. Most increases are approved within a few hours.
Learn AWS the Practical Way
Our bi-weekly newsletter teaches hands-on AWS fundamentals. No certification fluff - just practical knowledge.
Subscribe to NewsletterLearn AWS the Practical Way
Our bi-weekly newsletter teaches hands-on AWS fundamentals. No certification fluff - just practical knowledge.
Subscribe to Newsletter