# Priority Processing for Foundry Models

## Метаданные

- **Канал:** Microsoft Azure
- **YouTube:** https://www.youtube.com/watch?v=LwzLFeUJXiE
- **Источник:** https://ekstraktznaniy.ru/video/44727

## Транскрипт

### Segment 1 (00:00 - 01:00) []

Priority processing offers you latency SLA for consistent high-speed performance with pay as you go flexibility and no upfront commitments. Now available in Microsoft Foundry, it enables you to accelerate AI performance when you need it, starting with Azure OpenAI models. Deploying priority processing is simple. Use the same model and API just enable priority processing in your deployment settings. You’ll then access premium performance in select global and data zone regions. Monitor latency and optimize costs with built-in telemetry and recommendations. The result? Consistent, low-latency outcomes for your most demanding workloads, all backed by a platform you trust. It is perfect for real-time experiences in healthcare, financial services, and digital native apps where speed keeps users engaged Ready to deliver fast, reliable AI experiences? Turn on priority processing in Microsoft Foundry today and keep your users engaged and your business ahead.