# Batch API

> Batch API: An inference API that returns results later (often hours) in exchange for a lower price, for work that doesn't need an answer straight away.

Canonical: https://llmdojo.dev/glossary/batch-api

Also called batch APIs.

An inference API that returns results later (often hours) in exchange for a lower price, for work that doesn't need an answer straight away.

Learn it in the lesson: [Two prices per request](https://llmdojo.dev/learn/inference-optimization/cost-per-request/two-prices) (Inference and Model Optimization · Cost per Request and per Useful Answer).

## Interview questions about Batch API

- [How do you cut token costs at scale?](https://llmdojo.dev/interview/q/how-do-you-cut-token-costs-at-scale)
- [Design a backend where clients submit LLM prompt jobs and poll or receive callbacks, with queueing, model routing, prompt versioning, idempotency and cost control.](https://llmdojo.dev/interview/q/design-a-backend-where-clients-submit-llm-prompt-jobs-and-poll-or)

## Related
- [Cost per request](https://llmdojo.dev/glossary/cost-per-request)
- [Utilization](https://llmdojo.dev/glossary/utilization)
- [Cost per useful answer](https://llmdojo.dev/glossary/cost-per-useful-answer)
- [Glossary of every term](https://llmdojo.dev/glossary)