List batch inference jobs - Amazon Bedrock

List batch inference jobs


Batch inference is in preview and is subject to change. Batch inference is currently only available through the API. Access batch APIs through the following SDKs.

We recommend that you create a virtual environment to use the SDK. Because batch inference APIs aren't available in the latest SDKs, we recommend that you uninstall the latest version of the SDK from the virtual environment before installing the version with the batch inference APIs. For a guided example, see Code samples.

Request format
GET /model-invocation-jobs?maxResults=maxResults&nameContains=nameContains&nextToken=nextToken&sortBy=sortBy&sortOrder=sortOrder&statusEquals=statusEquals&submitTimeAfter=submitTimeAfter&submitTimeBefore=submitTimeBefore HTTP/1.1
Response format
HTTP/1.1 200 Content-type: application/json { "invocationJobSummaries": [ { "clientRequestToken": "string", "endTime": "string", "inputDataConfig": { "s3InputDataConfig": { "s3Uri": "string", "s3InputFormat": "JSONL" } }, "jobArn": "string", "jobName": "string", "lastModifiedTime": "string", "message": "string", "modelId": "string", "outputDataConfig": { "s3OutputDataConfig": { "s3Uri": "string" } }, "roleArn": "string", "status": "Submitted | InProgress | Completed | Failed | Stopping | Stopped", "submitTime": "string" } ], "nextToken": "string" }

To get information about a batch inference job, send a ListModelInvocationJobs. You can set the following specifications.

  • Filter for results by specifying the status, submission time, or substrings in the name of the job. You can specify the following statuses.

    • Submitted

    • InProgress

    • Completed

    • Failed

    • Stopping

    • Stopped

  • Sort by the time that the job was created (CreationTime). You can sort in Ascending or Descending order.

  • The maximum number of results to return in a response. If there are more results than the number you set, the response returns a nextToken that you can send in another ListModelInvocationJobs request to see the next batch of jobs.

The response returns a list of InvocationJobSummary objects. Each object contains information about a batch inference job.