Managed batch processing is now live

Point Docen at a queue of documents and let throughput scale itself up and back down. Managed batch is now generally available.

Hand off the backlog

Plenty of teams have a backlog: an archive to digitize, a quarter of invoices to reconcile, a corpus to index for retrieval. Standing up a pipeline to process it is real work, and most of that work is undifferentiated.

Managed batch takes the queue instead. You submit documents, and Docen handles routing, retries, back-pressure, and scaling. You get structured output and per-document status back.

• Per-document status and structured output
• Automatic retries and back-pressure
• Scales to millions of pages without standing infrastructure
• The same models and outputs as the real-time API

How it works

Throughput scales with the depth of your queue and settles back down when it drains, so you pay for the work rather than idle capacity.

Want to see it on your own documents? Open the playground or reach out — we're happy to run a sample with you.