---
type: "raw_signal"
id: "serverless-routing-made-sticky-8d0865"
slug: "serverless-routing-made-sticky-8d0865"
title: "Serverless routing made sticky"
description: "Modal announced Sticky Sessions for its serverless compute, adding session-level routing that directs every request in a session to the same container."
retrieval_nugget: "Modal announced Sticky Sessions for its serverless compute, adding session-level routing that directs every request in a session to the same container."
observed_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "observed_at"
why_it_matters: "This is a product capability release, not evidence of a general guarantee that application state survives container replacement. Modal’s post describes routing, authorization, load balancing, and scaling design, but does not provide independent performance or reliability measurements. Source: https://modal.com/blog/serverless-routing-made-sticky"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "modal.com"
topics: []
entities: ["Modal","Sticky Sessions","Modal Servers","Pipecat","Gradium Phonon"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Modal launched Sticky Sessions for serverless workloads that need requests routed to the same container; prior coverage concerned NVIDIA Dynamo’s session-aware inference routing."
prior_refs: ["memory:3e1fa5ff-2692-8e16-aebe-bd48e5c7c8cb"]
source_url: "https://modal.com/blog/serverless-routing-made-sticky"
source_urls: ["https://modal.com/blog/serverless-routing-made-sticky"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:serverless-routing-made-sticky-8d0865"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/serverless-routing-made-sticky-8d0865/","markdown":"https://newruntime.com/signals/serverless-routing-made-sticky-8d0865.md","json":"https://newruntime.com/signals/serverless-routing-made-sticky-8d0865.json"}
---

# Serverless routing made sticky

## Retrieval answer

Modal announced Sticky Sessions for its serverless compute, adding session-level routing that directs every request in a session to the same container.

Modal announced Sticky Sessions for its serverless compute, adding session-level routing that directs every request in a session to the same container. The company says the feature is intended for workloads that need continuity across reconnects, including voice agents, streaming speech-to-text, stateful web UIs, and multiplayer games.

The mechanism differs from request-level routing and the best-effort affinity previously available through Modal Servers. Session tokens carry routing metadata, while the container host tracks session lifecycle. Autoscaling uses active sessions and queued demand as inputs; containers can be configured to handle one or more concurrent sessions, and new sessions may queue when capacity is exhausted.

This is a product capability release, not evidence of a general guarantee that application state survives container replacement. Modal’s post describes routing, authorization, load balancing, and scaling design, but does not provide independent performance or reliability measurements. Source: https://modal.com/blog/serverless-routing-made-sticky

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)