Skip to main content
Batch inference complements the low-latency API when you need to score or enrich large portfolios.

When to choose batch

Use caseRecommended path
Nightly portfolio rescoringBatch
Real-time onboardingREST API
Marketing list enrichmentBatch
High-touch underwritingREST API with on-demand enrichment

Workflow

1

Upload data

Upload a file with model input data via the Batch API.
2

Submit job

Request a batch prediction via the Batch API specifying the previously uploaded file and an available model. Avra responds with a batch_id so you can track the job.
3

Processing

Jobs run in prioritized queues. Expect minutes for thousands of records and hours for millions.
4

Waiting

Poll GET /v1/api/batches/{id} checking job status or subscribe to the batch-lifecycle webhook to be notified on status transitions.
5

Download results

Request a download link at GET /v1/api/batches/{id}/result to obtain a single-use download URL to your result file.
Refer to the API Reference for endpoint schemas, payload examples, and error handling best practices when submitting batches.Workflow steps may vary when using SFTP Batch Inference. Please refer to the documentation for more details.

Limits

  • Up to 10M entities per batch by default — reach out for higher quotas.
  • Five concurrent batches per workspace.
  • CSV uploads capped at 500 MB.

Integrations

Monitoring

Track batch throughput and failures in the dashboard under Data Operations → Batches.