# What is Fluid Compute?

A serverless model where multiple requests can share one running function instance. It cuts cold starts and costs on workloads that spend time waiting, like AI API calls.

## In real work

Route AI requests through Fluid Compute. Five concurrent calls should share one warm instance, not spin up five cold ones.

## Related terms

- [Preview Deployment](https://prompthausapp.com/learn/preview-deployment.md)
- [ISR](https://prompthausapp.com/learn/isr.md)
- [Edge Network](https://prompthausapp.com/learn/edge-network.md)
- [Cold Start](https://prompthausapp.com/learn/cold-start.md)
- [Rollback](https://prompthausapp.com/learn/rollback.md)

## How is this different from Googling it?

Google gives a definition. Prompthaus pairs each term with how it shows up in standups, PRs, prompts, and design reviews—then quizzes you until the word sticks. One term a day on iPhone.

- Category: Launch
- HTML: https://prompthausapp.com/learn/fluid-compute
- App Store: https://apps.apple.com/us/app/prompthaus-ai-vocabulary/id6776314407