Amazon Bedrock endpoints and quotas
To connect programmatically to an AWS service, you use an endpoint. AWS services offer the following endpoint types in some or all of the AWS Regions that the service supports: IPv4 endpoints, dual-stack endpoints, and FIPS endpoints. Some services provide global endpoints. 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.
The following are the service endpoints and service quotas for this service.
Amazon Bedrock service endpoints
Amazon Bedrock control plane APIs
The following table provides a list of Region-specific endpoints that Amazon Bedrock supports for managing, training, and deploying models. Use these endpoints for Amazon Bedrock API operations.
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (Ohio) | us-east-2 |
bedrock.us-east-2.amazonaws.com bedrock-fips.us-east-2.amazonaws.com |
HTTPS HTTPS |
| US East (N. Virginia) | us-east-1 |
bedrock.us-east-1.amazonaws.com bedrock-fips.us-east-1.amazonaws.com |
HTTPS HTTPS |
| US West (N. California) | us-west-1 |
bedrock.us-west-1.amazonaws.com bedrock-fips.us-west-1.amazonaws.com |
HTTPS HTTPS |
| US West (Oregon) | us-west-2 |
bedrock.us-west-2.amazonaws.com bedrock-fips.us-west-2.amazonaws.com |
HTTPS HTTPS |
| Africa (Cape Town) | af-south-1 | bedrock.af-south-1.amazonaws.com | HTTPS |
| Asia Pacific (Hyderabad) | ap-south-2 | bedrock.ap-south-2.amazonaws.com | HTTPS |
| Asia Pacific (Jakarta) | ap-southeast-3 | bedrock.ap-southeast-3.amazonaws.com | HTTPS |
| Asia Pacific (Malaysia) | ap-southeast-5 | bedrock.ap-southeast-5.amazonaws.com | HTTPS |
| Asia Pacific (Melbourne) | ap-southeast-4 | bedrock.ap-southeast-4.amazonaws.com | HTTPS |
| Asia Pacific (Mumbai) | ap-south-1 | bedrock.ap-south-1.amazonaws.com | HTTPS |
| Asia Pacific (New Zealand) | ap-southeast-6 | bedrock.ap-southeast-6.amazonaws.com | HTTPS |
| Asia Pacific (Osaka) | ap-northeast-3 | bedrock.ap-northeast-3.amazonaws.com | HTTPS |
| Asia Pacific (Seoul) | ap-northeast-2 | bedrock.ap-northeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Singapore) | ap-southeast-1 | bedrock.ap-southeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 | bedrock.ap-southeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Taipei) | ap-east-2 | bedrock.ap-east-2.amazonaws.com | HTTPS |
| Asia Pacific (Thailand) | ap-southeast-7 | bedrock.ap-southeast-7.amazonaws.com | HTTPS |
| Asia Pacific (Tokyo) | ap-northeast-1 | bedrock.ap-northeast-1.amazonaws.com | HTTPS |
| Canada (Central) | ca-central-1 |
bedrock.ca-central-1.amazonaws.com bedrock-fips.ca-central-1.amazonaws.com |
HTTPS HTTPS |
| Canada West (Calgary) | ca-west-1 |
bedrock.ca-west-1.amazonaws.com bedrock-fips.ca-west-1.amazonaws.com |
HTTPS HTTPS |
| Europe (Frankfurt) | eu-central-1 | bedrock.eu-central-1.amazonaws.com | HTTPS |
| Europe (Ireland) | eu-west-1 | bedrock.eu-west-1.amazonaws.com | HTTPS |
| Europe (London) | eu-west-2 | bedrock.eu-west-2.amazonaws.com | HTTPS |
| Europe (Milan) | eu-south-1 | bedrock.eu-south-1.amazonaws.com | HTTPS |
| Europe (Paris) | eu-west-3 | bedrock.eu-west-3.amazonaws.com | HTTPS |
| Europe (Spain) | eu-south-2 | bedrock.eu-south-2.amazonaws.com | HTTPS |
| Europe (Stockholm) | eu-north-1 | bedrock.eu-north-1.amazonaws.com | HTTPS |
| Europe (Zurich) | eu-central-2 | bedrock.eu-central-2.amazonaws.com | HTTPS |
| Israel (Tel Aviv) | il-central-1 | bedrock.il-central-1.amazonaws.com | HTTPS |
| Mexico (Central) | mx-central-1 | bedrock.mx-central-1.amazonaws.com | HTTPS |
| Middle East (Bahrain) | me-south-1 | bedrock.me-south-1.amazonaws.com | HTTPS |
| Middle East (UAE) | me-central-1 | bedrock.me-central-1.amazonaws.com | HTTPS |
| South America (São Paulo) | sa-east-1 | bedrock.sa-east-1.amazonaws.com | HTTPS |
| AWS GovCloud (US-East) | us-gov-east-1 |
bedrock.us-gov-east-1.amazonaws.com bedrock-fips.us-gov-east-1.amazonaws.com |
HTTPS HTTPS |
| AWS GovCloud (US-West) | us-gov-west-1 |
bedrock.us-gov-west-1.amazonaws.com bedrock-fips.us-gov-west-1.amazonaws.com |
HTTPS HTTPS |
Amazon Bedrock runtime APIs
The following table provides a list of Region-specific endpoints that Amazon Bedrock supports for making inference requests for models hosted in Amazon Bedrock. Use these endpoints for Amazon Bedrock Runtime API operations.
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (Ohio) | us-east-2 |
bedrock-runtime.us-east-2.amazonaws.com bedrock-runtime-fips.us-east-2.amazonaws.com |
HTTPS HTTPS |
| US East (N. Virginia) | us-east-1 |
bedrock-runtime.us-east-1.amazonaws.com bedrock-runtime-fips.us-east-1.amazonaws.com |
HTTPS HTTPS |
| US West (Oregon) | us-west-2 |
bedrock-runtime.us-west-2.amazonaws.com bedrock-runtime-fips.us-west-2.amazonaws.com |
HTTPS HTTPS |
| Asia Pacific (Hyderabad) | ap-south-2 | bedrock-runtime.ap-south-2.amazonaws.com | HTTPS |
| Asia Pacific (Mumbai) | ap-south-1 | bedrock-runtime.ap-south-1.amazonaws.com | HTTPS |
| Asia Pacific (Osaka) | ap-northeast-3 | bedrock-runtime.ap-northeast-3.amazonaws.com | HTTPS |
| Asia Pacific (Seoul) | ap-northeast-2 | bedrock-runtime.ap-northeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Singapore) | ap-southeast-1 | bedrock-runtime.ap-southeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 | bedrock-runtime.ap-southeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Tokyo) | ap-northeast-1 | bedrock-runtime.ap-northeast-1.amazonaws.com | HTTPS |
| Canada (Central) | ca-central-1 |
bedrock-runtime.ca-central-1.amazonaws.com bedrock-runtime-fips.ca-central-1.amazonaws.com |
HTTPS HTTPS |
| Europe (Frankfurt) | eu-central-1 | bedrock-runtime.eu-central-1.amazonaws.com | HTTPS |
| Europe (Ireland) | eu-west-1 | bedrock-runtime.eu-west-1.amazonaws.com | HTTPS |
| Europe (London) | eu-west-2 | bedrock-runtime.eu-west-2.amazonaws.com | HTTPS |
| Europe (Milan) | eu-south-1 | bedrock-runtime.eu-south-1.amazonaws.com | HTTPS |
| Europe (Paris) | eu-west-3 | bedrock-runtime.eu-west-3.amazonaws.com | HTTPS |
| Europe (Spain) | eu-south-2 | bedrock-runtime.eu-south-2.amazonaws.com | HTTPS |
| Europe (Stockholm) | eu-north-1 | bedrock-runtime.eu-north-1.amazonaws.com | HTTPS |
| Europe (Zurich) | eu-central-2 | bedrock-runtime.eu-central-2.amazonaws.com | HTTPS |
| South America (São Paulo) | sa-east-1 | bedrock-runtime.sa-east-1.amazonaws.com | HTTPS |
| AWS GovCloud (US-East) | us-gov-east-1 |
bedrock-runtime.us-gov-east-1.amazonaws.com bedrock-runtime-fips.us-gov-east-1.amazonaws.com |
HTTPS HTTPS |
| AWS GovCloud (US-West) | us-gov-west-1 |
bedrock-runtime.us-gov-west-1.amazonaws.com bedrock-runtime-fips.us-gov-west-1.amazonaws.com |
HTTPS HTTPS |
Agents for Amazon Bedrock build-time APIs
The following table provides a list of Region-specific endpoints that Agents for Amazon Bedrock supports for creating and managing agents and knowledge bases. Use these endpoints for Agents for Amazon Bedrock API operations.
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (N. Virginia) | us-east-1 | bedrock-agent.us-east-1.amazonaws.com | HTTPS |
| bedrock-agent-fips.us-east-1.amazonaws.com | HTTPS | ||
| US West (Oregon) | us-west-2 | bedrock-agent.us-west-2.amazonaws.com | HTTPS |
| bedrock-agent-fips.us-west-2.amazonaws.com | HTTPS | ||
| Asia Pacific (Singapore) | ap-southeast-1 | bedrock-agent.ap-southeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 | bedrock-agent.ap-southeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Tokyo) | ap-northeast-1 | bedrock-agent.ap-northeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Seoul) | ap-northeast-2 | bedrock-agent.ap-northeast-2.amazonaws.com | HTTPS |
| Canada (Central) | ca-central-1 | bedrock-agent.ca-central-1.amazonaws.com | HTTPS |
| Europe (Frankfurt) | eu-central-1 | bedrock-agent.eu-central-1.amazonaws.com | HTTPS |
| Europe (Ireland) | eu-west-1 | bedrock-agent.eu-west-1.amazonaws.com | HTTPS |
| Europe (London) | eu-west-2 | bedrock-agent.eu-west-2.amazonaws.com | HTTPS |
| Europe (Paris) | eu-west-3 | bedrock-agent.eu-west-3.amazonaws.com | HTTPS |
| Asia Pacific (Mumbai) | ap-south-1 | bedrock-agent.ap-south-1.amazonaws.com | HTTPS |
| South America (São Paulo) | sa-east-1 | bedrock-agent.sa-east-1.amazonaws.com | HTTPS |
Agents for Amazon Bedrock runtime APIs
The following table provides a list of Region-specific endpoints that Agents for Amazon Bedrock supports for invoking agents and querying knowledge bases. Use these endpoints for Agents for Amazon Bedrock Runtime API operations.
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (N. Virginia) | us-east-1 | bedrock-agent-runtime.us-east-1.amazonaws.com | HTTPS |
| bedrock-agent-runtime-fips.us-east-1.amazonaws.com | HTTPS | ||
| US West (Oregon) | us-west-2 | bedrock-agent-runtime.us-west-2.amazonaws.com | HTTPS |
| bedrock-agent-runtime-fips.us-west-2.amazonaws.com | HTTPS | ||
| Asia Pacific (Singapore) | ap-southeast-1 | bedrock-agent-runtime.ap-southeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 | bedrock-agent-runtime.ap-southeast-2.amazonaws.com | HTTPS |
| Asia Pacific (Tokyo) | ap-northeast-1 | bedrock-agent-runtime.ap-northeast-1.amazonaws.com | HTTPS |
| Asia Pacific (Seoul) | ap-northeast-2 | bedrock-agent-runtime.ap-northeast-2.amazonaws.com | HTTPS |
| Canada (Central) | ca-central-1 | bedrock-agent-runtime.ca-central-1.amazonaws.com | HTTPS |
| Europe (Frankfurt) | eu-central-1 | bedrock-agent-runtime.eu-central-1.amazonaws.com | HTTPS |
| Europe (Paris) | eu-west-3 | bedrock-agent-runtime.eu-west-3.amazonaws.com | HTTPS |
| Europe (Ireland) | eu-west-1 | bedrock-agent-runtime.eu-west-1.amazonaws.com | HTTPS |
| Europe (London) | eu-west-2 | bedrock-agent-runtime.eu-west-2.amazonaws.com | HTTPS |
| Asia Pacific (Mumbai) | ap-south-1 | bedrock-agent-runtime.ap-south-1.amazonaws.com | HTTPS |
| South America (São Paulo) | sa-east-1 | bedrock-agent-runtime.sa-east-1.amazonaws.com | HTTPS |
Amazon Bedrock Data Automation APIs
The following table provides a list of Region-specific endpoints that Data Automation for Amazon Bedrock supports.
Endpoints that use the word runtime invoke blueprints and projects to extract information from files.
Use these endpoints for Amazon Bedrock Data Automation Runtime API operations. Endpoints without runtime are used to
create blueprints and projects to provide extraction guidance. Use these endpoints for Amazon Bedrock Data Automation API Buildtime operations
| Region Name | Region | Endpoint | Protocol |
|---|---|---|---|
| US East (Ohio) | us-east-2 |
bedrock-data-automation.us-east-2.amazonaws.com bedrock-data-automation-runtime.us-east-2.amazonaws.com bedrock-data-automation-fips.us-east-2.amazonaws.com bedrock-data-automation-runtime-fips.us-east-2.amazonaws.com |
HTTPS HTTPS HTTPS HTTPS |
| US East (N. Virginia) | us-east-1 |
bedrock-data-automation.us-east-1.amazonaws.com bedrock-data-automation-runtime.us-east-1.api.aws bedrock-data-automation-runtime.us-east-1.amazonaws.com bedrock-data-automation.us-east-1.api.aws bedrock-data-automation-fips.us-east-1.amazonaws.com bedrock-data-automation-runtime-fips.us-east-1.api.aws bedrock-data-automation-runtime-fips.us-east-1.amazonaws.com bedrock-data-automation-fips.us-east-1.api.aws |
HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS |
| US West (Oregon) | us-west-2 |
bedrock-data-automation.us-west-2.amazonaws.com bedrock-data-automation-runtime.us-west-2.api.aws bedrock-data-automation-runtime.us-west-2.amazonaws.com bedrock-data-automation.us-west-2.api.aws bedrock-data-automation-fips.us-west-2.amazonaws.com bedrock-data-automation-runtime-fips.us-west-2.api.aws bedrock-data-automation-runtime-fips.us-west-2.amazonaws.com bedrock-data-automation-fips.us-west-2.api.aws |
HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS HTTPS |
| Asia Pacific (Mumbai) | ap-south-1 |
bedrock-data-automation.ap-south-1.amazonaws.com bedrock-data-automation-runtime.ap-south-1.amazonaws.com |
HTTPS HTTPS |
| Asia Pacific (Sydney) | ap-southeast-2 |
bedrock-data-automation.ap-southeast-2.amazonaws.com bedrock-data-automation-runtime.ap-southeast-2.amazonaws.com |
HTTPS HTTPS |
| Asia Pacific (Tokyo) | ap-northeast-1 |
bedrock-data-automation.ap-northeast-1.amazonaws.com bedrock-data-automation-runtime.ap-northeast-1.amazonaws.com |
HTTPS HTTPS |
| Canada (Central) | ca-central-1 |
bedrock-data-automation.ca-central-1.amazonaws.com bedrock-data-automation-runtime.ca-central-1.amazonaws.com bedrock-data-automation-fips.ca-central-1.amazonaws.com bedrock-data-automation-runtime-fips.ca-central-1.amazonaws.com |
HTTPS HTTPS HTTPS HTTPS |
| Europe (Frankfurt) | eu-central-1 |
bedrock-data-automation.eu-central-1.amazonaws.com bedrock-data-automation-runtime.eu-central-1.amazonaws.com |
HTTPS HTTPS |
| Europe (Ireland) | eu-west-1 |
bedrock-data-automation.eu-west-1.amazonaws.com bedrock-data-automation-runtime.eu-west-1.amazonaws.com |
HTTPS HTTPS |
| Europe (London) | eu-west-2 |
bedrock-data-automation.eu-west-2.amazonaws.com bedrock-data-automation-runtime.eu-west-2.amazonaws.com |
HTTPS HTTPS |
| Europe (Spain) | eu-south-2 |
bedrock-data-automation.eu-south-2.amazonaws.com bedrock-data-automation-runtime.eu-south-2.amazonaws.com |
HTTPS HTTPS |
| AWS GovCloud (US-West) | us-gov-west-1 |
bedrock-data-automation.us-gov-west-1.amazonaws.com bedrock-data-automation-runtime.us-gov-west-1.amazonaws.com bedrock-data-automation-fips.us-gov-west-1.amazonaws.com bedrock-data-automation-runtime-fips.us-gov-west-1.amazonaws.com |
HTTPS HTTPS HTTPS HTTPS |
Amazon Bedrock service quotas
Tip
Because Amazon Bedrock has a large number of quotas, we recommend that you view the service quotas using the
console instead of using the table below. Open Amazon Bedrock quotas
| Name | Default | Adjustable | Description |
|---|---|---|---|
| (Advanced Prompt Optimization) Active jobs per account | Each supported Region: 20 |
Yes |
The maximum number of active Advanced Prompt Optimization (APO) jobs per account. |
| (Advanced Prompt Optimization) Inactive jobs per account | Each supported Region: 5,000 |
Yes |
The maximum number of inactive Advanced Prompt Optimization (APO) jobs per account. |
| (Automated Reasoning) Annotations in policy | Each supported Region: 10 | No | The maximum number of annotations in an Automated Reasoning policy. |
| (Automated Reasoning) CancelAutomatedReasoningPolicyBuildWorkflow requests per second | Each supported Region: 5 |
Yes |
The maximum number of CancelAutomatedReasoningPolicyBuildWorkflow API requests per second. |
| (Automated Reasoning) Concurrent builds per policy | Each supported Region: 2 | No | The maximum number of concurrent builds per Automated Reasoning policy. |
| (Automated Reasoning) Concurrent policy builds per account | Each supported Region: 5 | No | The maximum number of concurrent Automated Reasoning policy builds in one account. |
| (Automated Reasoning) CreateAutomatedReasoningPolicy requests per second | Each supported Region: 5 |
Yes |
The maximum number of CreateAutomatedReasoningPolicy API requests per second. |
| (Automated Reasoning) CreateAutomatedReasoningPolicyTestCase requests per second | Each supported Region: 5 |
Yes |
The maximum number of CreateAutomatedReasoningPolicyTestCase API requests per second. |
| (Automated Reasoning) CreateAutomatedReasoningPolicyVersion requests per second | Each supported Region: 5 |
Yes |
The maximum number of CreateAutomatedReasoningPolicyVersion API requests per second. |
| (Automated Reasoning) DeleteAutomatedReasoningPolicy requests per second | Each supported Region: 5 |
Yes |
The maximum number of DeleteAutomatedReasoningPolicy API requests per second. |
| (Automated Reasoning) DeleteAutomatedReasoningPolicyBuildWorkflow requests per second | Each supported Region: 5 |
Yes |
The maximum number of DeleteAutomatedReasoningPolicyBuildWorkflow API requests per second. |
| (Automated Reasoning) DeleteAutomatedReasoningPolicyTestCase requests per second | Each supported Region: 5 |
Yes |
The maximum number of DeleteAutomatedReasoningPolicyTestCase API requests per second. |
| (Automated Reasoning) ExportAutomatedReasoningPolicyVersion requests per second | Each supported Region: 5 |
Yes |
The maximum number of ExportAutomatedReasoningPolicyVersion API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicy requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicy API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyAnnotations requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyAnnotations API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyBuildWorkflow requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyBuildWorkflow API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyBuildWorkflowResultAssets requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyBuildWorkflowResultAssets API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyNextScenario requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyNextScenario API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyTestCase requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyTestCase API requests per second. |
| (Automated Reasoning) GetAutomatedReasoningPolicyTestResult requests per second | Each supported Region: 10 |
Yes |
The maximum number of GetAutomatedReasoningPolicyTestResult API requests per second. |
| (Automated Reasoning) ListAutomatedReasoningPolicies requests per second | Each supported Region: 5 |
Yes |
The maximum number of ListAutomatedReasoningPolicies API requests per second. |
| (Automated Reasoning) ListAutomatedReasoningPolicyBuildWorkflows requests per second | Each supported Region: 5 |
Yes |
The maximum number of ListAutomatedReasoningPolicyBuildWorkflows API requests per second. |
| (Automated Reasoning) ListAutomatedReasoningPolicyTestCases requests per second | Each supported Region: 5 |
Yes |
The maximum number of ListAutomatedReasoningPolicyTestCases API requests per second. |
| (Automated Reasoning) ListAutomatedReasoningPolicyTestResults requests per second | Each supported Region: 5 |
Yes |
The maximum number of ListAutomatedReasoningPolicyTestResults API requests per second. |
| (Automated Reasoning) Policies per account | Each supported Region: 100 | No | The maximum number of Automated Reasoning policies in one account. |
| (Automated Reasoning) Rules in policy | Each supported Region: 500 | No | The maximum number of rules in an Automated Reasoning policy. |
| (Automated Reasoning) Source document size (MB) | Each supported Region: 5 | No | The maximum source document size (MB) for creating an Automated Reasoning policy. |
| (Automated Reasoning) Source document tokens | Each supported Region: 122,880 | No | The maximum number of tokens allowed in a source document when creating an Automated Reasoning policy. |
| (Automated Reasoning) StartAutomatedReasoningPolicyBuildWorkflow requests per second | Each supported Region: 1 |
Yes |
The maximum number of StartAutomatedReasoningPolicyBuildWorkflow API requests per second. |
| (Automated Reasoning) StartAutomatedReasoningPolicyTestWorkflow requests per second | Each supported Region: 1 |
Yes |
The maximum number of StartAutomatedReasoningPolicyTestWorkflow API requests per second. |
| (Automated Reasoning) Tests per policy | Each supported Region: 100 | No | The maximum number of tests per Automated Reasoning policy. |
| (Automated Reasoning) Types per policy | Each supported Region: 50 | No | The maximum number of types in an Automated Reasoning policy. |
| (Automated Reasoning) UpdateAutomatedReasoningPolicy requests per second | Each supported Region: 5 |
Yes |
The maximum number of UpdateAutomatedReasoningPolicy API requests per second. |
| (Automated Reasoning) UpdateAutomatedReasoningPolicyAnnotations requests per second | Each supported Region: 5 |
Yes |
The maximum number of UpdateAutomatedReasoningPolicyAnnotations API requests per second. |
| (Automated Reasoning) UpdateAutomatedReasoningPolicyTestCase requests per second | Each supported Region: 5 |
Yes |
The maximum number of UpdateAutomatedReasoningPolicyTestCase API requests per second. |
| (Automated Reasoning) Values per type in policy | Each supported Region: 50 | No | The maximum number of values per type in an Automated Reasoning policy. |
| (Automated Reasoning) Variables in policy | Each supported Region: 200 | No | The maximum number of variables in an Automated Reasoning policy. |
| (Automated Reasoning) Versions per policy | Each supported Region: 1,000 | No | The maximum number of versions per Automated Reasoning policy. |
| (Data Automation) (Console) Maximum document file size (MB) | Each supported Region: 200 | No | The maximum file size for console |
| (Data Automation) (Console) Maximum number of pages per document file | Each supported Region: 20 | No | The maximum number of pages per document in console |
| (Data Automation) CreateBlueprint - Max number of blueprints per account | Each supported Region: 350 |
Yes |
The maximum number of blueprints per account |
| (Data Automation) CreateBlueprintVersion - Max number of Blueprint versions per Blueprint | Each supported Region: 10 |
Yes |
The maximum number of versions per blueprint |
| (Data Automation) CreateDataAutomationLibrary - Max number of data automation libraries per account | Each supported Region: 10 |
Yes |
The maximum number of data automation libraries per account |
| (Data Automation) Description length for fields (Characters) | Each supported Region: 300 | No | The maximum length of description for fields in characters |
| (Data Automation) InvokeBlueprintOptimizationAsync - Max number of blueprint optimization concurrent jobs | Each supported Region: 3 |
Yes |
The maximum number of Invoke Blueprint Optimization Async open jobs |
| (Data Automation) InvokeBlueprintOptimizationAsync - Max number of blueprint optimization jobs per day | Each supported Region: 30 | No | The maximum number of Invoke Blueprint Optimization Async jobs per day |
| (Data Automation) InvokeDataAutomation(Sync) - Document - Max number of requests | Each supported Region: 60 |
Yes |
The maximum number of InvokeDataAutomation requests per minute for document modality |
| (Data Automation) InvokeDataAutomationAsync - Audio - Max number of concurrent jobs |
us-east-1: 20 us-west-2: 20 Each of the other supported Regions: 2 |
Yes |
The maximum number of Invoke Data Automation Async open jobs for audios |
| (Data Automation) InvokeDataAutomationAsync - Document - Max number of concurrent jobs |
ap-south-1: 5 ca-central-1: 5 eu-south-2: 5 eu-west-2: 5 Each of the other supported Regions: 25 |
Yes |
The maximum number of Invoke Data Automation Async open jobs for documents |
| (Data Automation) InvokeDataAutomationAsync - Image - Max number of concurrent jobs |
us-east-1: 20 us-west-2: 20 Each of the other supported Regions: 5 |
Yes |
The maximum number of Invoke Data Automation Async open jobs for images |
| (Data Automation) InvokeDataAutomationAsync - Max number of open jobs | Each supported Region: 1,800 | No | The maximum number of Invoke Data Automation Async open jobs for images |
| (Data Automation) InvokeDataAutomationAsync - Video - Max number of concurrent jobs |
us-east-1: 20 us-west-2: 20 Each of the other supported Regions: 3 |
Yes |
The maximum number of Invoke Data Automation Async open jobs for videos |
| (Data Automation) Max number of vocabulary phrases per library | Each supported Region: 500 |
Yes |
The maximum number of custom vocabulary phrases that can be configured per library |
| (Data Automation) Maximum Audio Sample Rate (Hz) | Each supported Region: 48,000 | No | The maximum audio sample rate |
| (Data Automation) Maximum Blueprints per Project (Audios) | Each supported Region: 1 | No | The maximum number of blueprints per projects for audios |
| (Data Automation) Maximum Blueprints per Project (Documents) | Each supported Region: 40 | No | The maximum number of blueprints per projects for documents |
| (Data Automation) Maximum Blueprints per Project (Images) | Each supported Region: 1 | No | The maximum number of blueprints per projects for images |
| (Data Automation) Maximum Blueprints per Project (Videos) | Each supported Region: 1 | No | The maximum number of blueprints per projects for videos |
| (Data Automation) Maximum JSON Blueprint Size (Characters) | Each supported Region: 100,000 | No | The maximum size of JSON in Characters |
| (Data Automation) Maximum Levels of Field Hierarchy | Each supported Region: 1 | No | The maximum number level of field hierarchy |
| (Data Automation) Maximum Number of pages per document | Each supported Region: 3,000 | No | The maximum number of pages per document |
| (Data Automation) Maximum Resolution | Each supported Region: 8,000 | No | The maximum resolution for Images |
| (Data Automation) Maximum audio file size (MB) | Each supported Region: 2,048 | No | The maximum file size for Audio |
| (Data Automation) Maximum audio length (Minutes) | Each supported Region: 240 | No | The maximum length for audio in minutes |
| (Data Automation) Maximum document file size (MB) | Each supported Region: 500 | No | The maximum file size |
| (Data Automation) Maximum image file size (MB) | Each supported Region: 5 | No | The maximum file size for Images |
| (Data Automation) Maximum instruction field length for Audio Blueprint - (Characters) | Each supported Region: 500 |
Yes |
The maximum length of instruction field for audio blueprint in characters |
| (Data Automation) Maximum number of Blueprints per Start Inference request (Audios) | Each supported Region: 1 | No | The maximum number of inline blueprint in Start inference request |
| (Data Automation) Maximum number of Blueprints per Start Inference request (Documents) | Each supported Region: 10 | No | The maximum number of inline blueprint in Start inference request |
| (Data Automation) Maximum number of Blueprints per Start Inference request (Images) | Each supported Region: 1 | No | The maximum number of inline blueprint in Start inference request |
| (Data Automation) Maximum number of Blueprints per Start Inference request (Videos) | Each supported Region: 1 | No | The maximum number of inline blueprint in Start inference request |
| (Data Automation) Maximum number of list fields per Blueprint | Each supported Region: 15 | No | The maximum number of list fields per Blueprint |
| (Data Automation) Maximum video file size (MB) | Each supported Region: 10,240 | No | The maximum file size for Videos |
| (Data Automation) Maximum video length (Minutes) | Each supported Region: 240 | No | The maximum length for videos in minutes |
| (Data Automation) Minimum Audio Sample Rate (Hz) | Each supported Region: 8,000 | No | The minimum audio sample rate |
| (Data Automation) Minimum audio length (Miliseconds) | Each supported Region: 500 | No | The minimum length for audio in miliseconds |
| (Evaluation) Number of concurrent automatic model evaluation jobs | Each supported Region: 20 | No | The maximum number of automatic model evaluation jobs that you can specify at one time in this account in the current Region. |
| (Evaluation) Number of concurrent model evaluation jobs that use human workers | Each supported Region: 10 | No | The maximum number of model evaluation jobs that use human workers you can specify at one time in this account in the current Region. |
| (Evaluation) Number of custom metrics | Each supported Region: 10 | No | The maximum number of custom metrics that you can specify in a model evaluation job that uses human workers. |
| (Evaluation) Number of custom prompt datasets in a human-based model evaluation job | Each supported Region: 1 | No | The maximum number of custom prompt datasets that you can specify in a human-based model evaluation job in this account in the current Region. |
| (Evaluation) Number of datasets per job | Each supported Region: 5 | No | The maximum number of datasets that you can specify in an automated model evaluation job. This includes both custom and built-in prompt datasets. |
| (Evaluation) Number of evaluation jobs | Each supported Region: 5,000 | No | The maximum number of model evaluation jobs that you can create in this account in the current Region. |
| (Evaluation) Number of metrics per dataset | Each supported Region: 3 | No | The maximum number of metrics that you can specify per dataset in an automated model evaluation job. This includes both custom and built-in metrics. |
| (Evaluation) Number of models in a model evaluation job that uses human workers | Each supported Region: 2 | No | The maximum number of models that you can specify in a model evaluation job that uses human workers. |
| (Evaluation) Number of models in automated model evaluation job | Each supported Region: 1 | No | The maximum number of models that you can specify in an automated model evaluation job. |
| (Evaluation) Number of prompts in a custom prompt dataset | Each supported Region: 1,000 | No | The maximum number of prompts a custom prompt dataset can contain. |
| (Evaluation) Size of prompt | Each supported Region: 4 | No | The maximum size (in KB) of an individual prompt in a custom prompt dataset. |
| (Evaluation) Task time for workers | Each supported Region: 30 | No | The maximum length (in days) of time that a worker can have to complete tasks. |
| (Flows) Agent nodes per flow | Each supported Region: 20 | No | The maximum number of agent nodes. |
| (Flows) Collector nodes per flow | Each supported Region: 1 | No | The maximum number of collector nodes. |
| (Flows) Condition nodes per flow | Each supported Region: 5 | No | The maximum number of condition nodes. |
| (Flows) Conditions per condition node | Each supported Region: 5 | No | The maximum number of conditions per condition node. |
| (Flows) CreateFlow requests per second | Each supported Region: 2 | No | The maximum number of CreateFlow requests per second. |
| (Flows) CreateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowAlias requests per second. |
| (Flows) CreateFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of CreateFlowVersion requests per second. |
| (Flows) DeleteFlow requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlow requests per second. |
| (Flows) DeleteFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowAlias requests per second. |
| (Flows) DeleteFlowVersion requests per second | Each supported Region: 2 | No | The maximum number of DeleteFlowVersion requests per second. |
| (Flows) Flow aliases per flow | Each supported Region: 10 | No | The maximum number of flow aliases. |
| (Flows) Flow executions per account | Each supported Region: 1,000 |
Yes |
The maximum number of flow executions per account. |
| (Flows) Flow versions per flow | Each supported Region: 10 | No | The maximum number of flow versions. |
| (Flows) Flows per account | Each supported Region: 100 |
Yes |
The maximum number of flows per account. |
| (Flows) GetFlow requests per second | Each supported Region: 10 | No | The maximum number of GetFlow requests per second. |
| (Flows) GetFlowAlias requests per second | Each supported Region: 10 | No | The maximum number of GetFlowAlias requests per second. |
| (Flows) GetFlowVersion requests per second | Each supported Region: 10 | No | The maximum number of GetFlowVersion requests per second. |
| (Flows) Inline code nodes per flow | Each supported Region: 5 | No | The maximum number of inline code nodes per flow. |
| (Flows) Input nodes per flow | Each supported Region: 1 | No | The maximum number of flow input nodes. |
| (Flows) Iterator nodes per flow | Each supported Region: 1 | No | The maximum number of iterator nodes. |
| (Flows) Knowledge base nodes per flow | Each supported Region: 20 | No | The maximum number of knowledge base nodes. |
| (Flows) Lambda function nodes per flow | Each supported Region: 20 | No | The maximum number of Lambda function nodes. |
| (Flows) Lex nodes per flow | Each supported Region: 5 | No | The maximum number of Lex nodes. |
| (Flows) ListFlowAliases requests per second | Each supported Region: 10 | No | The maximum number of ListFlowAliases requests per second. |
| (Flows) ListFlowVersions requests per second | Each supported Region: 10 | No | The maximum number of ListFlowVersions requests per second. |
| (Flows) ListFlows requests per second | Each supported Region: 10 | No | The maximum number of ListFlows requests per second. |
| (Flows) Output nodes per flow | Each supported Region: 20 | No | The maximum number of flow output nodes. |
| (Flows) PrepareFlow requests per second | Each supported Region: 2 | No | The maximum number of PrepareFlow requests per second. |
| (Flows) Prompt nodes per flow | Each supported Region: 20 |
Yes |
The maximum number of prompt nodes. |
| (Flows) S3 retrieval nodes per flow | Each supported Region: 10 | No | The maximum number of S3 retrieval nodes. |
| (Flows) S3 storage nodes per flow | Each supported Region: 10 | No | The maximum number of S3 storage nodes. |
| (Flows) Total nodes per flow | Each supported Region: 40 | No | The maximum number of nodes in a flow. |
| (Flows) UpdateFlow requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlow requests per second. |
| (Flows) UpdateFlowAlias requests per second | Each supported Region: 2 | No | The maximum number of UpdateFlowAlias requests per second. |
| (Flows) ValidateFlowDefinition requests per second | Each supported Region: 2 | No | The maximum number of ValidateFlowDefinition requests per second. |
| (Guardrails) Automated Reasoning policies per guardrail | Each supported Region: 2 | No | The maximum number of Automated Reasoning policies per guardrail. |
| (Guardrails) Content policy maximum input size in text units (Classic tier) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 eu-south-1: 25 eu-west-3: 25 sa-east-1: 25 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed for content filters. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) Content policy maximum input size in text units (Standard tier - Recommended) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 500 ap-northeast-2: 1,000 ap-south-1: 500 ap-southeast-1: 1,000 ap-southeast-2: 400 eu-central-1: 500 eu-south-1: 25 eu-west-1: 1,000 eu-west-3: 25 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed for content filters. This applies to the standard tier, which is recommended. |
| (Guardrails) Contextual grounding policy maximum input size in text units | Each supported Region: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed by Contextual grounding policies |
| (Guardrails) Contextual grounding query length in text units | Each supported Region: 1 | No | The maximum length, in text units, of the query for contextual grounding |
| (Guardrails) Contextual grounding response length in text units | Each supported Region: 5 | No | The maximum length, in text units, of the response for contextual grounding |
| (Guardrails) Contextual grounding source length in text units |
us-east-1: 100 us-west-2: 100 Each of the other supported Regions: 50 |
No | The maximum length, in text units, of the grounding source for contextual grounding |
| (Guardrails) Example phrases per Topic | Each supported Region: 5 | No | The maximum number of topic examples that can be included per topic |
| (Guardrails) Guardrails per account | Each supported Region: 100 | No | The maximum number of guardrails in an account |
| (Guardrails) On-demand ApplyGuardrail Content filter policy text units burst rate (Classic tier) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for content filters. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) On-demand ApplyGuardrail Content filter policy text units burst rate (Standard tier - Recommended) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 500 ap-northeast-2: 1,000 ap-south-1: 500 ap-southeast-1: 1,000 ap-southeast-2: 400 eu-central-1: 500 eu-west-1: 1,000 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for content filters. This applies to the standard tier, which is recommended. |
| (Guardrails) On-demand ApplyGuardrail Content filter policy text units per second (Classic tier) |
us-east-1: 200 us-west-2: 200 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for content filters. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) On-demand ApplyGuardrail Content filter policy text units per second (Standard tier - Recommended) |
us-east-1: 200 us-east-2: 200 us-west-1: 200 us-west-2: 200 ap-northeast-1: 50 ap-northeast-2: 100 ap-south-1: 50 ap-southeast-1: 100 eu-central-1: 50 eu-west-1: 200 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for content filters. This applies to the standard tier, which is recommended. |
| (Guardrails) On-demand ApplyGuardrail Denied topic policy text units burst rate (Classic tier) |
us-east-1: 200 us-west-2: 200 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for denied topics. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) On-demand ApplyGuardrail Denied topic policy text units burst rate (Standard tier - Recommended) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 500 ap-northeast-2: 1,000 ap-south-1: 500 ap-southeast-1: 1,000 ap-southeast-2: 400 eu-central-1: 500 eu-west-1: 1,000 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for denied topics. This applies to the standard tier, which is recommended. |
| (Guardrails) On-demand ApplyGuardrail Denied topic policy text units per second (Classic tier) |
us-east-1: 50 us-west-2: 50 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for denied topics. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) On-demand ApplyGuardrail Denied topic policy text units per second (Standard tier - Recommended) |
us-east-1: 200 us-east-2: 75 us-west-1: 75 us-west-2: 200 eu-west-1: 200 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for denied topics. This applies to the standard tier, which is recommended. |
| (Guardrails) On-demand ApplyGuardrail Sensitive information filter policy text units burst rate |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for sensitive information filters. |
| (Guardrails) On-demand ApplyGuardrail Sensitive information filter policy text units per second |
us-east-1: 1,000 us-east-2: 100 us-west-1: 50 us-west-2: 500 ap-northeast-1: 500 ap-northeast-2: 100 ap-northeast-3: 75 ap-south-1: 200 ap-south-2: 75 ap-southeast-1: 100 ap-southeast-2: 250 ca-central-1: 250 eu-central-1: 500 eu-central-2: 75 eu-north-1: 75 eu-south-1: 75 eu-south-2: 50 eu-west-1: 500 eu-west-2: 100 eu-west-3: 250 sa-east-1: 75 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for sensitive information filters. |
| (Guardrails) On-demand ApplyGuardrail Word filter policy text units burst rate |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 Each of the other supported Regions: 25 |
No | The maximum number of text units in one burst that can be processed for word filters. |
| (Guardrails) On-demand ApplyGuardrail Word filter policy text units per second |
us-east-1: 500 us-east-2: 500 us-west-1: 500 us-west-2: 500 ap-northeast-1: 500 ap-northeast-2: 500 ap-south-1: 500 ap-southeast-1: 500 eu-central-1: 500 Each of the other supported Regions: 25 |
Yes |
The maximum number of text units per second that can be processed for word filters. |
| (Guardrails) On-demand ApplyGuardrail contextual grounding policy text units burst rate | Each supported Region: 106 | No | The maximum number of text units in one burst that can be processed for contextual grounding. |
| (Guardrails) On-demand ApplyGuardrail contextual grounding policy text units per second | Each supported Region: 106 |
Yes |
The maximum number of text units per second that can be processed for contextual grounding. |
| (Guardrails) On-demand ApplyGuardrail requests burst rate |
us-east-1: 100 us-east-2: 100 us-west-1: 100 us-west-2: 100 ap-northeast-1: 100 ap-northeast-2: 100 ap-south-1: 100 ap-southeast-1: 100 eu-central-1: 100 Each of the other supported Regions: 25 |
No | The maximum number of ApplyGuardrail API calls that you can send in one burst. |
| (Guardrails) On-demand ApplyGuardrail requests per second |
us-east-1: 100 us-east-2: 100 us-west-1: 100 us-west-2: 100 ap-northeast-1: 100 ap-northeast-2: 100 ap-south-1: 100 ap-southeast-1: 100 eu-central-1: 100 Each of the other supported Regions: 25 |
Yes |
The maximum number of ApplyGuardrail API calls allowed per second |
| (Guardrails) On-demand InvokeGuardrailChecks requests burst rate | Each supported Region: 1,500 | No | The maximum number of InvokeGuardrailChecks API calls that you can send in one burst |
| (Guardrails) On-demand InvokeGuardrailChecks requests per minute | Each supported Region: 1,500 |
Yes |
The maximum number of InvokeGuardrailChecks API calls allowed per minute |
| (Guardrails) Regex entities in Sensitive Information Filter | Each supported Region: 30 | No | The maximum number of guardrail filter regexes that can be included in a sensitive information policy |
| (Guardrails) Regex length in characters | Each supported Region: 500 | No | The maximum length, in characters, of a guardrail filter regex |
| (Guardrails) Sensitive information policy maximum input size in text units |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed by Sensitive information filter policies |
| (Guardrails) Topic policy maximum input size in text units (Classic tier) |
us-east-1: 200 us-west-2: 200 ap-southeast-1: 25 eu-south-1: 25 eu-west-3: 25 sa-east-1: 25 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed for denied topics. While this limit applies to the classic tier, we recommend migrating to standard tier due to its superior robustness, additional capabilities, and multi-lingual support. |
| (Guardrails) Topic policy maximum input size in text units (Standard tier - Recommended) |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 500 ap-northeast-2: 1,000 ap-south-1: 500 ap-southeast-1: 1,000 ap-southeast-2: 400 eu-central-1: 500 eu-south-1: 25 eu-west-1: 1,000 eu-west-3: 25 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed for denied topics. This applies to the standard tier, which is recommended. |
| (Guardrails) Topics per guardrail | Each supported Region: 30 | No | The maximum number of topics that can be defined across guardrail topic policies |
| (Guardrails) Versions per guardrail | Each supported Region: 20 | No | The maximum number of versions that a guardrail can have |
| (Guardrails) Word length in characters | Each supported Region: 100 | No | The maximum length of a word, in characters, in a blocked word list |
| (Guardrails) Word policy maximum input size in text units |
us-east-1: 1,000 us-east-2: 1,000 us-west-2: 1,000 ap-northeast-1: 1,000 ap-northeast-2: 1,000 ap-south-1: 1,000 ap-southeast-1: 1,000 ap-southeast-2: 1,000 eu-central-1: 1,000 Each of the other supported Regions: 106 |
Yes |
The maximum size of input text, measured in text units, that can be processed by Word filter policies |
| (Guardrails) Words per word policy | Each supported Region: 10,000 | No | The maximum number of words that can be included in a blocked word list |
| (Knowledge Bases) Concurrent IngestKnowledgeBaseDocuments and DeleteKnowledgeBaseDocuments requests per account | Each supported Region: 10 | No | The maximum number of IngestKnowledgeBaseDocuments and DeleteKnowledgeBaseDocuments requests that can be running at the same time in an account. |
| (Knowledge Bases) Concurrent ingestion jobs per account | Each supported Region: 5 | No | The maximum number of ingestion jobs that can be running at the same time in an account. |
| (Knowledge Bases) Concurrent ingestion jobs per data source | Each supported Region: 1 | No | The maximum number of ingestion jobs that can be running at the same time for a data source. |
| (Knowledge Bases) Concurrent ingestion jobs per knowledge base | Each supported Region: 1 | No | The maximum number of ingestion jobs that can be running at the same time for a knowledge base. |
| (Knowledge Bases) CreateDataSource requests per second | Each supported Region: 2 | No | The maximum number of CreateDataSource API requests per second. |
| (Knowledge Bases) CreateKnowledgeBase requests per second | Each supported Region: 2 | No | The maximum number of CreateKnowledgeBase API requests per second. |
| (Knowledge Bases) Data sources per knowledge base | Each supported Region: 5 | No | The maximum number of data sources per knowledge base. |
| (Knowledge Bases) DeleteDataSource requests per second | Each supported Region: 2 | No | The maximum number of DeleteDataSource API requests per second. |
| (Knowledge Bases) DeleteKnowledgeBase requests per second | Each supported Region: 2 | No | The maximum number of DeleteKnowledgeBase API requests per second. |
| (Knowledge Bases) DeleteKnowledgeBaseDocuments requests per second | Each supported Region: 5 | No | The maximum number of DeleteKnowledgeBaseDocuments API requests per second. |
| (Knowledge Bases) Files to add or update per ingestion job | Each supported Region: 5,000,000 | No | The maximum number of new and updated files that can be ingested per ingestion job. |
| (Knowledge Bases) Files to delete per ingestion job | Each supported Region: 5,000,000 | No | The maximum number of files that can be deleted per ingestion job. |
| (Knowledge Bases) Files to ingest per IngestKnowledgeBaseDocuments job. | Each supported Region: 25 | No | The maximum number of documents that can be ingested per IngestKnowledgeBaseDocuments request. |
| (Knowledge Bases) GenerateQuery requests per second | Each supported Region: 2 | No | The maximum number of GenerateQuery API requests per second. |
| (Knowledge Bases) GetDataSource requests per second | Each supported Region: 10 | No | The maximum number of GetDataSource API requests per second. |
| (Knowledge Bases) GetIngestionJob requests per second | Each supported Region: 10 | No | The maximum number of GetIngestionJob API requests per second. |
| (Knowledge Bases) GetKnowledgeBase requests per second | Each supported Region: 10 | No | The maximum number of GetKnowledgeBase API requests per second. |
| (Knowledge Bases) GetKnowledgeBaseDocuments requests per second | Each supported Region: 5 | No | The maximum number of GetKnowledgeBaseDocuments API requests per second. |
| (Knowledge Bases) IngestKnowledgeBaseDocuments requests per second | Each supported Region: 5 | No | The maximum number of IngestKnowledgeBaseDocuments API requests per second. |
| (Knowledge Bases) IngestKnowledgeBaseDocuments total payload size | Each supported Region: 6 | No | The maximum size (in MB) of total payload in an IngestKnowledgeBaseDocuments request. |
| (Knowledge Bases) Ingestion job file size with text content | Each supported Region: 50 | No | The maximum size (in MB) of a file with text content (such as .txt, .pdf, or .docx files) in an ingestion job. |
| (Knowledge Bases) Ingestion job size | Each supported Region: 100 | No | The maximum size (in GB) of an ingestion job. |
| (Knowledge Bases) Knowledge bases per account | Each supported Region: 100 | No | The maximum number of knowledge bases per account. |
| (Knowledge Bases) ListDataSources requests per second | Each supported Region: 10 | No | The maximum number of ListDataSources API requests per second. |
| (Knowledge Bases) ListIngestionJobs requests per second | Each supported Region: 10 | No | The maximum number of ListIngestionJobs API requests per second. |
| (Knowledge Bases) ListKnowledgeBaseDocuments requests per second | Each supported Region: 5 | No | The maximum number of ListKnowledgeBaseDocuments API requests per second. |
| (Knowledge Bases) ListKnowledgeBases requests per second | Each supported Region: 10 | No | The maximum number of ListKnowledgeBases API requests per second. |
| (Knowledge Bases) Maximum number of files for BDA parser | Each supported Region: 1,000 | No | The maximum number of files that can be used with Amazon Bedrock Data Automation as parser. |
| (Knowledge Bases) Maximum number of files for Foundation Models as a parser | Each supported Region: 1,000 | No | The maximum number of files that can be used with Foundation Models as a parser. |
| (Knowledge Bases) Rerank requests per second | Each supported Region: 10 | No | The maximum number of Rerank API requests per second. |
| (Knowledge Bases) Retrieve requests per second | Each supported Region: 20 | No | The maximum number of Retrieve API requests per second. |
| (Knowledge Bases) RetrieveAndGenerate requests per second | Each supported Region: 20 | No | The maximum number of RetrieveAndGenerate API requests per second. |
| (Knowledge Bases) RetrieveAndGenerateStream requests per second | Each supported Region: 20 | No | The maximum number of RetrieveAndGenerateStream API requests per second. |
| (Knowledge Bases) StartIngestionJob requests per second | Each supported Region: 0.1 | No | The maximum number of StartIngestionJob API requests per second. |
| (Knowledge Bases) UpdateDataSource requests per second | Each supported Region: 2 | No | The maximum number of UpdateDataSource API requests per second. |
| (Knowledge Bases) UpdateKnowledgeBase requests per second | Each supported Region: 2 | No | The maximum number of UpdateKnowledgeBase API requests per second. |
| (Knowledge Bases) User query size | Each supported Region: 1,000 | No | The maximum size (in characters) of a user query. |
| (Managed Knowledge Bases) AgenticRetrieveStream requests per minute per account | Each supported Region: 60 | No | The maximum number of AgenticRetrieveStream API requests per minute per account for Managed KBs. |
| (Managed Knowledge Bases) AgenticRetrieveStream user query size | Each supported Region: 10,000 | No | The maximum size (in characters) of a user query for AgenticRetrieveStream for Managed KBs. |
| (Managed Knowledge Bases) Concurrent ingestion jobs per knowledge base | Each supported Region: 50 | No | The maximum number of concurrent ingestion jobs per Managed KB. |
| (Managed Knowledge Bases) Data sources per knowledge base | Each supported Region: 200 | No | The maximum number of data sources per Managed KB. |
| (Managed Knowledge Bases) DeleteKnowledgeBaseDocuments requests per second | Each supported Region: 10 | No | The maximum number of DeleteKnowledgeBaseDocuments API requests per second for Managed KBs. |
| (Managed Knowledge Bases) DeleteResourcePolicy requests per second | Each supported Region: 5 | No | The maximum number of DeleteResourcePolicy API requests per second for Managed KBs. |
| (Managed Knowledge Bases) Files to ingest per IngestKnowledgeBaseDocuments request | Each supported Region: 10 | No | The maximum number of files to ingest per IngestKnowledgeBaseDocuments API request for Managed KBs. |
| (Managed Knowledge Bases) GetDocumentContent requests per second per account | Each supported Region: 100 | No | The maximum number of GetDocumentContent API requests per second per account. |
| (Managed Knowledge Bases) GetDocumentContent requests per second per knowledge base | Each supported Region: 5 | No | The maximum number of GetDocumentContent API requests per second per Managed KB. |
| (Managed Knowledge Bases) GetResourcePolicy requests per second | Each supported Region: 5 | No | The maximum number of GetResourcePolicy API requests per second for Managed KBs. |
| (Managed Knowledge Bases) Individual file extracted text size (MB) | Each supported Region: 30 | No | The maximum size (in MB) of extracted text from a single file for Managed KBs. |
| (Managed Knowledge Bases) IngestKnowledgeBaseDocuments requests per second | Each supported Region: 20 | No | The maximum number of IngestKnowledgeBaseDocuments API requests per second for Managed KBs. |
| (Managed Knowledge Bases) Knowledge bases per account | Each supported Region: 10,000 | No | The maximum number of Managed KBs per account. |
| (Managed Knowledge Bases) ListKnowledgeBaseDocuments requests per second | Each supported Region: 10 | No | The maximum number of ListKnowledgeBaseDocuments API requests per second for Managed KBs. |
| (Managed Knowledge Bases) PutResourcePolicy requests per second | Each supported Region: 5 | No | The maximum number of PutResourcePolicy API requests per second for Managed KBs. |
| (Managed Knowledge Bases) Retrieve requests per minute per knowledge base | Each supported Region: 600 | No | The maximum number of Retrieve API requests per minute per Managed KB. |
| (Managed Knowledge Bases) Retrieve requests per second per account | Each supported Region: 100 | No | The maximum number of Retrieve API requests per second per account for Managed KBs. |
| (Managed Knowledge Bases) Retrieve user query size | Each supported Region: 10,000 | No | The maximum size (in characters) of a user query for Retrieve for Managed KBs. |
| (Managed Knowledge Bases) Total storage size per knowledge base (TB) | Each supported Region: 10 | No | The maximum total storage size (in TB) per Managed KB. |
| (Model customization) Custom models per account | Each supported Region: 100 |
Yes |
The maximum number of custom models in an account. |
| (Model customization) In-progress custom model deployments | Each supported Region: 2 |
Yes |
The maximum number of in-progress custom model deployments |
| (Model customization) Maximum input file size for distillation customization jobs | Each supported Region: 2 Gigabytes | No | The maximum input file size for distillation customization jobs. |
| (Model customization) Maximum line length for distillation customization jobs | Each supported Region: 16 Kilobytes | No | The maximum line length in input file for distillation customization jobs. |
| (Model customization) Maximum number of prompts for distillation customization jobs | Each supported Region: 15,000 | No | The maximum number of prompts required for distillation customization jobs. |
| (Model customization) Maximum number of training records for an Amazon Nova Canvas Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum number of records allowed for an Amazon Nova Canvas Fine-tuning job. |
| (Model customization) Maximum student model fine tuning context length for Amazon Nova Micro V1 distillation customization jobs | Each supported Region: 32,000 | No | The maximum student model fine tuning context length for Amazon Nova Micro V1 distillation customization jobs. |
| (Model customization) Maximum student model fine tuning context length for Amazon Nova V1 distillation customization jobs | Each supported Region: 32,000 | No | The maximum student model fine tuning context length for Amazon Nova V1 distillation customization jobs. |
| (Model customization) Maximum student model fine tuning context length for Anthropic Claude 3 haiku 20240307 V1 distillation customization jobs | Each supported Region: 32,000 | No | The maximum student model fine tuning context length for Anthropic Claude 3 haiku 20240307 V1 distillation customization jobs. |
| (Model customization) Maximum student model fine tuning context length for Llama 3.1 70B Instruct V1 distillation customization jobs | Each supported Region: 16,000 | No | The maximum student model fine tuning context length for Llama 3.1 70B Instruct V1 distillation customization jobs. |
| (Model customization) Maximum student model fine tuning context length for Llama 3.1 8B Instruct V1 distillation customization jobs | Each supported Region: 32,000 | No | The maximum student model fine tuning context length for Llama 3.1 8B Instruct V1 distillation customization jobs. |
| (Model customization) Minimum number of prompts for distillation customization jobs | Each supported Region: 100 | No | The minimum number of prompts required for distillation customization jobs. |
| (Model customization) Scheduled customization jobs | Each supported Region: 10 | No | The maximum number of scheduled customization jobs. |
| (Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova 2 Lite | Each supported Region: 2,000 | No | The sum of input and output on-demand custom model deployment requests per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova 2 Lite |
| (Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Lite | Each supported Region: 2,000 | No | The sum of input and output on-demand custom model deployment requests per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Lite |
| (Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Micro | Each supported Region: 2,000 | No | The sum of input and output on-demand custom model deployment requests per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Micro |
| (Model customization) Sum of on demand custom model deployment requests per minute for Amazon Nova Pro | Each supported Region: 200 | No | The sum of input and output on-demand custom model deployment requests per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Pro |
| (Model customization) Sum of on demand custom model deployment requests per minute for Meta Llama 3.3 70B Instruct | Each supported Region: 400 | No | The sum of input and output on-demand custom model deployment requests per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Meta Llama 3.3 70B Instruct |
| (Model customization) Sum of on demand custom model deployment tokens per day for Amazon Nova 2 Lite | Each supported Region: 5,760,000,000 | No | The sum of input and output on-demand custom model deployment tokens per day submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova 2 Lite |
| (Model customization) Sum of on demand custom model deployment tokens per day for Amazon Nova Lite | Each supported Region: 5,760,000,000 | No | The sum of input and output on-demand custom model deployment tokens per day submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Lite |
| (Model customization) Sum of on demand custom model deployment tokens per day for Amazon Nova Micro | Each supported Region: 5,760,000,000 | No | The sum of input and output on-demand custom model deployment tokens per day submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Micro |
| (Model customization) Sum of on demand custom model deployment tokens per day for Amazon Nova Pro | Each supported Region: 1,152,000,000 | No | The sum of input and output on-demand custom model deployment tokens per day submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Pro |
| (Model customization) Sum of on demand custom model deployment tokens per day for Meta Llama 3.3 70B Instruct | Each supported Region: 432,000,000 | No | The sum of input and output on-demand custom model deployment tokens per day submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Meta Llama 3.3 70B Instruct |
| (Model customization) Sum of on demand custom model deployment tokens per minute for Amazon Nova 2 Lite | Each supported Region: 4,000,000 | No | The sum of input and output on-demand custom model deployment tokens per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova 2 Lite |
| (Model customization) Sum of on demand custom model deployment tokens per minute for Amazon Nova Lite | Each supported Region: 4,000,000 | No | The sum of input and output on-demand custom model deployment tokens per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Lite |
| (Model customization) Sum of on demand custom model deployment tokens per minute for Amazon Nova Micro | Each supported Region: 4,000,000 | No | The sum of input and output on-demand custom model deployment tokens per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Micro |
| (Model customization) Sum of on demand custom model deployment tokens per minute for Amazon Nova Pro | Each supported Region: 800,000 | No | The sum of input and output on-demand custom model deployment tokens per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Amazon Nova Pro |
| (Model customization) Sum of on demand custom model deployment tokens per minute for Meta Llama 3.3 70B Instruct | Each supported Region: 300,000 | No | The sum of input and output on-demand custom model deployment tokens per minute submitted to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream actions for Meta Llama 3.3 70B Instruct |
| (Model customization) Sum of training and validation records for a Amazon Nova 2 Lite Fine-tuning job | Each supported Region: 20,000 |
Yes |
The maximum combined number of training and validation records allowed for a Amazon Nova 2 Lite Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Amazon Nova Lite Fine-tuning job | Each supported Region: 20,000 |
Yes |
The maximum combined number of training and validation records allowed for a Amazon Nova Lite Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Amazon Nova Micro Fine-tuning job | Each supported Region: 20,000 |
Yes |
The maximum combined number of training and validation records allowed for a Amazon Nova Micro Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Amazon Nova Pro Fine-tuning job | Each supported Region: 20,000 |
Yes |
The maximum combined number of training and validation records allowed for a Amazon Nova Pro Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Claude 3 Haiku v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Claude 3 Haiku Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Claude 3-5-Haiku v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Claude 3-5-Haiku Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 2 13B v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 2 13B Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 2 70B v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 2 70B Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.1 70B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.1 70B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.1 8B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.1 8B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.2 11B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.2 11B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.2 1B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.2 1B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.2 3B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.2 3B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.2 90B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.2 90B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Meta Llama 3.3 70B Instruct v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Meta Llama 3.3 70B Instruct Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Image Generator G1 V1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Image Generator Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Image Generator G1 V2 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Image Generator V2 Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Multimodal Embeddings G1 v1 Fine-tuning job | Each supported Region: 50,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Multimodal Embeddings Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Text G1 - Express v1 Continued Pre-Training job | Each supported Region: 100,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Text Express Continued Pre-Training job. |
| (Model customization) Sum of training and validation records for a Titan Text G1 - Express v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Text Express Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Text G1 - Lite v1 Continued Pre-Training job | Each supported Region: 100,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Text Lite Continued Pre-Training job. |
| (Model customization) Sum of training and validation records for a Titan Text G1 - Lite v1 Fine-tuning job | Each supported Region: 10,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Text Lite Fine-tuning job. |
| (Model customization) Sum of training and validation records for a Titan Text G1 - Premier v1 Fine-tuning job | Each supported Region: 20,000 |
Yes |
The maximum combined number of training and validation records allowed for a Titan Text Premier Fine-tuning job. |
| (Model customization) Total number of custom model deployments | Each supported Region: 10 |
Yes |
Total number of custom model deployments |
| (Prompt management) CreatePrompt requests per second | Each supported Region: 2 | No | The maximum number of CreatePrompt requests per second. |
| (Prompt management) CreatePromptVersion requests per second | Each supported Region: 2 | No | The maximum number of CreatePromptVersion requests per second. |
| (Prompt management) DeletePrompt requests per second | Each supported Region: 2 | No | The maximum number of DeletePrompt requests per second. |
| (Prompt management) GetPrompt requests per second | Each supported Region: 10 | No | The maximum number of GetPrompt requests per second. |
| (Prompt management) ListPrompts requests per second | Each supported Region: 10 | No | The maximum number of ListPrompts requests per second. |
| (Prompt management) Prompts per account | Each supported Region: 500 |
Yes |
The maximum number of prompts. |
| (Prompt management) UpdatePrompt requests per second | Each supported Region: 2 | No | The maximum number of UpdatePrompt requests per second. |
| (Prompt management) Versions per prompt | Each supported Region: 10 | No | The maximum number of versions per prompt. |
| APIs per Agent | Each supported Region: 11 |
Yes |
The maximum number of APIs that you can add to an Agent. |
| Action groups per Agent | Each supported Region: 20 |
Yes |
The maximum number of action groups that you can add to an Agent. |
| Agent Collaborators per Agent | Each supported Region: 1,000 |
Yes |
The maximum number of collaborator agents that you can add to an Agent. |
| Agents per account | Each supported Region: 1,000 |
Yes |
The maximum number of Agents in one account. |
| AssociateAgentKnowledgeBase requests per second | Each supported Region: 6 | No | The maximum number of AssociateAgentKnowledgeBase API requests per second. |
| Associated aliases per Agent | Each supported Region: 10 | No | The maximum number of aliases that you can associate with an Agent. |
| Associated knowledge bases per Agent | Each supported Region: 2 |
Yes |
The maximum number of knowledge bases that you can associate with an Agent. |
| Batch inference input file size (in GB) for Amazon Nova 2 Multimodal Embeddings V1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Amazon Nova 2 Multimodal Embeddings V1. |
| Batch inference input file size (in GB) for Amazon Nova Premier | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Amazon Nova Premier. |
| Batch inference input file size (in GB) for Claude 3 Haiku | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude 3 Haiku. |
| Batch inference input file size (in GB) for Claude 3 Opus | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude 3 Opus. |
| Batch inference input file size (in GB) for Claude 3.5 Haiku | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude 3.5 Haiku. |
| Batch inference input file size (in GB) for Claude 3.7 Sonnet | Each supported Region: 1 |
Yes |
The maximum size of a single file (in GB) submitted for batch inference for Claude 3.7 Sonnet. |
| Batch inference input file size (in GB) for Claude Haiku 4.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Haiku 4.5. |
| Batch inference input file size (in GB) for Claude Opus 4.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Opus 4.5. |
| Batch inference input file size (in GB) for Claude Opus 4.6 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Opus 4.6. |
| Batch inference input file size (in GB) for Claude Opus 5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Opus 5. |
| Batch inference input file size (in GB) for Claude Sonnet 4 | Each supported Region: 1 |
Yes |
The maximum size of a single file (in GB) submitted for batch inference for Claude Sonnet 4. |
| Batch inference input file size (in GB) for Claude Sonnet 4.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Sonnet 4.5. |
| Batch inference input file size (in GB) for Claude Sonnet 4.6 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Claude Sonnet 4.6. |
| Batch inference input file size (in GB) for DeepSeek V3.2 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for DeepSeek V3.2. |
| Batch inference input file size (in GB) for DeepSeek v3 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for DeepSeek v3. |
| Batch inference input file size (in GB) for Devstral 2 123B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Devstral 2 123B. |
| Batch inference input file size (in GB) for GLM 4.7 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for GLM 4.7. |
| Batch inference input file size (in GB) for GLM 4.7 Flash | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for GLM 4.7 Flash. |
| Batch inference input file size (in GB) for GLM 5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for GLM 5. |
| Batch inference input file size (in GB) for Gemma 3 12B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Gemma 3 12B. |
| Batch inference input file size (in GB) for Gemma 3 27B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Gemma 3 27B. |
| Batch inference input file size (in GB) for Gemma 3 4B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Gemma 3 4B. |
| Batch inference input file size (in GB) for Kimi K2 Thinking | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Kimi K2 Thinking. |
| Batch inference input file size (in GB) for Kimi K2.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Kimi K2.5. |
| Batch inference input file size (in GB) for Llama 3.1 405B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.1 405B Instruct. |
| Batch inference input file size (in GB) for Llama 3.1 70B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.1 70B Instruct. |
| Batch inference input file size (in GB) for Llama 3.1 8B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.1 8B Instruct. |
| Batch inference input file size (in GB) for Llama 3.2 11B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.2 11B Instruct. |
| Batch inference input file size (in GB) for Llama 3.2 1B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference Llama 3.2 1B Instruct. |
| Batch inference input file size (in GB) for Llama 3.2 3B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.2 3B Instruct. |
| Batch inference input file size (in GB) for Llama 3.2 90B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.2 90B Instruct. |
| Batch inference input file size (in GB) for Llama 3.3 70B Instruct | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 3.3 70B Instruct. |
| Batch inference input file size (in GB) for Llama 4 Maverick | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 4 Maverick. |
| Batch inference input file size (in GB) for Llama 4 Scout | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Llama 4 Scout. |
| Batch inference input file size (in GB) for Magistral Small 2509 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Magistral Small 2509. |
| Batch inference input file size (in GB) for MiniMax M2 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for MiniMax M2. |
| Batch inference input file size (in GB) for MiniMax M2.1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for MiniMax M2.1. |
| Batch inference input file size (in GB) for MiniMax M2.5 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for MiniMax M2.5. |
| Batch inference input file size (in GB) for Ministral 3 14B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Ministral 3 14B. |
| Batch inference input file size (in GB) for Ministral 3 8B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Ministral 3 8B. |
| Batch inference input file size (in GB) for Ministral 3B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Ministral 3B. |
| Batch inference input file size (in GB) for Mistral Large 2 (24.07) | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Mistral Large 2 (24.07). |
| Batch inference input file size (in GB) for Mistral Large 3 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Mistral Large 3. |
| Batch inference input file size (in GB) for Mistral Small | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Mistral Small. |
| Batch inference input file size (in GB) for NVIDIA Nemotron 3 Super 120B A12B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for NVIDIA Nemotron 3 Super 120B A12B. |
| Batch inference input file size (in GB) for NVIDIA Nemotron Nano 12B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for NVIDIA Nemotron Nano 12B. |
| Batch inference input file size (in GB) for NVIDIA Nemotron Nano 3 30B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for NVIDIA Nemotron Nano 3 30B. |
| Batch inference input file size (in GB) for NVIDIA Nemotron Nano 9B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for NVIDIA Nemotron Nano 9B. |
| Batch inference input file size (in GB) for Nova 2 Lite | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Nova 2 Lite. |
| Batch inference input file size (in GB) for Nova Lite V1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Nova Lite V1. |
| Batch inference input file size (in GB) for Nova Micro V1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Nova Micro V1. |
| Batch inference input file size (in GB) for Nova Pro V1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Nova Pro V1. |
| Batch inference input file size (in GB) for OpenAI GPT OSS 120b | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for OpenAI GPT OSS 120b. |
| Batch inference input file size (in GB) for OpenAI GPT OSS 20b | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for OpenAI GPT OSS 20b. |
| Batch inference input file size (in GB) for OpenAI GPT OSS Safeguard 120b | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for OpenAI GPT OSS Safeguard 120b. |
| Batch inference input file size (in GB) for OpenAI GPT OSS Safeguard 20b | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for OpenAI GPT OSS Safeguard 20b. |
| Batch inference input file size (in GB) for Qwen3 235B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 235B. |
| Batch inference input file size (in GB) for Qwen3 32B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 32B. |
| Batch inference input file size (in GB) for Qwen3 Coder 30B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 Coder 30B. |
| Batch inference input file size (in GB) for Qwen3 Coder 480B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 Coder 480B. |
| Batch inference input file size (in GB) for Qwen3 Coder Next | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 Coder Next. |
| Batch inference input file size (in GB) for Qwen3 Next 80B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 Next 80B. |
| Batch inference input file size (in GB) for Qwen3 VL 235B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Qwen3 VL 235B. |
| Batch inference input file size (in GB) for Titan Multimodal Embeddings G1 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Titan Multimodal Embeddings G1. |
| Batch inference input file size (in GB) for Titan Text Embeddings V2 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Titan Text Embeddings V2. |
| Batch inference input file size (in GB) for Voxtral Mini 3B 2507 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Voxtral Mini 3B 2507. |
| Batch inference input file size (in GB) for Voxtral Small 24B 2507 | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Voxtral Small 24B 2507. |
| Batch inference input file size (in GB) for Writer Palmyra Vision 7B | Each supported Region: 1 | No | The maximum size of a single file (in GB) submitted for batch inference for Writer Palmyra Vision 7B. |
| Batch inference job size (in GB) for Qwen3 Next 80B | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Qwen3 Next 80B. |
| Batch inference job size (in GB) for Amazon Nova 2 Multimodal Embeddings V1 | Each supported Region: 100 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Amazon Nova 2 Multimodal Embeddings V1. |
| Batch inference job size (in GB) for Amazon Nova Premier | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Amazon Nova Premier. |
| Batch inference job size (in GB) for Claude 3 Haiku | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude 3 Haiku. |
| Batch inference job size (in GB) for Claude 3 Opus | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude 3 Opus. |
| Batch inference job size (in GB) for Claude 3.5 Haiku | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude 3.5 Haiku. |
| Batch inference job size (in GB) for Claude 3.7 Sonnet | Each supported Region: 5 |
Yes |
The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude 3.7 Sonnet. |
| Batch inference job size (in GB) for Claude Haiku 4.5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Haiku 4.5. |
| Batch inference job size (in GB) for Claude Opus 4.5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Opus 4.5. |
| Batch inference job size (in GB) for Claude Opus 4.6 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Opus 4.6. |
| Batch inference job size (in GB) for Claude Opus 5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Opus 5. |
| Batch inference job size (in GB) for Claude Sonnet 4 | Each supported Region: 5 |
Yes |
The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Sonnet 4. |
| Batch inference job size (in GB) for Claude Sonnet 4.5 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Sonnet 4.5. |
| Batch inference job size (in GB) for Claude Sonnet 4.6 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Claude Sonnet 4.6. |
| Batch inference job size (in GB) for DeepSeek V3.2 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for DeepSeek V3.2. |
| Batch inference job size (in GB) for DeepSeek v3 | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for DeepSeek v3. |
| Batch inference job size (in GB) for Devstral 2 123B | Each supported Region: 5 | No | The maximum cumulative size of all input files (in GB) included in the batch inference job for Devstral 2 123B. |