# Vercel — Introducing Fluid compute

- Company: Vercel (vercel.com)
- Announced: 2025-02-04T13:00:00+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://vercel.com/blog/introducing-fluid-compute
- Record: https://forck.live/items/20902-introducing-fluid-compute
- Subject: v0 / AI SDK / AI Gateway

Vercel introduced Fluid compute, a new execution model for Vercel Functions that combines serverless efficiency with server-like flexibility. It reduces compute costs by up to 85%, minimizes cold starts, supports advanced tasks like streaming and post-response processing, and is available for all users today with no code changes required.

## Evidence

Verbatim from https://vercel.com/blog/introducing-fluid-compute:

> Fluid compute evolves beyond serverless, trading single-invocation functions for high-performance mini-servers. This model has helped thousands of early adopters maximize resource efficiency, minimize cold starts, and reduce compute costs by up to 85% .

---

Record: https://forck.live/items/20902-introducing-fluid-compute
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md