Artificial intelligence news.
Straight from the original announcements.

Vercel makes WebSocket support in Functions generally available

October 20, 2026Source: Vercel
Vercel makes WebSocket support in Functions generally available
Image: Vercel

Vercel has made WebSocket support in Vercel Functions generally available, ending a public beta that began in late June. According to Vercel, its CDN has served 300 million WebSocket connections since the beta launch and now serves 15 million per day.

Key points
  • WebSocket support in Vercel Functions is now generally available after a public beta that began in late June.
  • According to Vercel, its CDN has served 300 million WebSocket connections and now serves 15 million per day.
  • Customers use WebSockets for AI chat, streaming, and realtime multiplayer apps, and they power AI Gateway's realtime models.
  • WebSocket connections follow the same limits and pricing as other Function invocations.
  • With Active CPU pricing, CPU is billed only for the time spent processing messages.

From public beta to general availability

Vercel announced that WebSocket support in Vercel Functions has moved out of beta. The public beta launched in late June, and the company says usage has grown quickly since then. Vercel reports that its CDN has served 300 million WebSocket connections over that period and now handles 15 million per day.

WebSockets keep a connection open between client and server, which allows data to flow in both directions without repeated requests. That makes them a common choice for applications that need to push updates to users as they happen.

How customers use WebSockets

According to Vercel, customers use WebSockets for AI chat, streaming, and realtime multiplayer apps. The company also says WebSockets power the realtime models in its AI Gateway, so the feature is used inside Vercel's own AI infrastructure as well as in customer projects.

The listed use cases reflect where interactive, low-latency communication matters most: conversational AI interfaces, continuous data streams, and shared multiplayer experiences where several users see changes at once.

Pricing and limits

Vercel states that WebSocket connections follow the same limits and pricing as other Function invocations. Developers therefore do not face a separate pricing model for this type of connection.

With Active CPU pricing, CPU is billed only for the time spent processing messages. In practice, this means the periods when a connection is open but idle are not billed as CPU time, according to the way Vercel describes the model. This matters for realtime apps, where connections can stay open for long stretches with only occasional message traffic.

What it means for developers

The move to general availability signals that Vercel considers the feature ready for production workloads. Teams building AI chat, streaming, or multiplayer applications on Vercel Functions can use WebSockets under the existing limits and pricing, with billing tied to message processing time rather than connection time under Active CPU pricing.

Vercel points developers to its documentation to get started. The changelog entry credits Mark Glagola, Ethan Niser, and Casey Gowrie as contributors.

Related news

Vercel Adds DeepSeek V4.1 Flash 1017 Ultrafast to AI Gateway
Products and toolsNovember 7, 2026

Vercel Adds DeepSeek V4.1 Flash 1017 Ultrafast to AI Gateway

Vercel has added DeepSeek V4.1 Flash 1017 Ultrafast to its AI Gateway through Fireworks, giving developers access to a model that can generate upwards of 1,000 tokens…

Vercel adds DeepSeek Search and Fetch to AI Gateway
For developersNovember 6, 2026

Vercel adds DeepSeek Search and Fetch to AI Gateway

Vercel has added DeepSeek Search and DeepSeek Fetch to AI Gateway, allowing developers to give models web search and page retrieval tools through one AI Gateway API key.…

Vercel Automatically Applies Token Pass Credit Across AI Gateway
Products and toolsNovember 5, 2026, 22:30

Vercel Automatically Applies Token Pass Credit Across AI Gateway

Vercel says Token Pass credit now applies automatically to included model usage through AI Gateway, regardless of whether a request uses an API key, an OIDC token, or fx…