# Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent

DevFeed: [Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent](<https://devfeed.tech/articles/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-1126.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent>)

Author: Elisabeth Rülke

Published: 2026-08-07T19:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Vercel](<https://devfeed.tech/topics/vercel.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>), [Terminal](<https://devfeed.tech/topics/terminal.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [inference](<https://devfeed.tech/tags/inference.md>), [models](<https://devfeed.tech/tags/models.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [terminal](<https://devfeed.tech/tags/terminal.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

## AI overview

The release adds Vercel AI Gateway and Vercel Sandbox support to Hermes Agent. Hermes can use AI Gateway to access more than 200 models with no token markup, live model availability and pricing, and usage tracking in the AI Gateway dashboard. Its commands can also run in an isolated Vercel Sandbox cloud microVM instead of locally when the opt-in backend is enabled.

## Source excerpt

Hermes Agent can now use Vercel AI Gateway as its inference layer and run its agent commands in an isolated Vercel Sandbox microVM. Access 200+ models through AI Gateway at no markup on tokens, and every request appears in your AI Gateway dashboard with the rest of your usage and spend. Setup Install Hermes, then pick Vercel AI Gateway in the setup wizard: The picker pulls live model availability and current pricing from AI Gateway. For the full walkthrough, see Configuring Hermes. Running commands in Vercel Sandbox The Vercel Sandbox backend is opt-in. Commands run locally until you set terminal.backend to vercel_sandbox; with it enabled, agent commands run in a cloud microVM with a workspace root of /vercel/sandbox instead of on your machine. The backend supports node24 (default), node22, and python3.13 runtimes. For local development, use VERCEL_OIDC_TOKEN. Run vercel link and vercel env pull to get a development token. To get started, read the Hermes documentation and the Vercel Sandbox documentation, or browse AI Gateway models. Read more