Runtime – Your AI Agents Have a Home

Runtime launched agent sandboxes that run a full Linux microVM per AI agent at up to 6× lower cost than E2B and Daytona, with a new sandbox running 102 ms after the create request and its first Python command completing 221 ms later, measured on Runtime's servers in Virginia on 28 September 2026. Runtime bills $0.025 per active vCPU-hour above a default floor of a twentieth of a vCPU and $0.0075 per GiB-hour of memory, and says the same agent job costs 42% to 88% less than at fourteen other providers. Code written for E2B, Daytona, Vercel Sandbox or Blaxel runs by changing one import, and idle sandboxes pause after 60 seconds for $0.08 per GB a month.

Runtime https://withruntime.com/sandbox Agent sandboxes.Up to 6× cheaper. A full Linux microVM per agent. First result in 221 ms. Start free, no card https://withruntime.com/account Integrations Run any code. A Linux machine in 102 ms. - Pauses when idle Pays storage only, and is back in 76 ms. - No time limit Runs as long as the work does. - Root and Docker apt, sudo and Compose inside. Bring any environment. Your own Dockerfile. - Any Dockerfile or registry image - Built once, versioned - Docker runs inside How images work https://withruntime.com/docs/images web:v1 every sandbox starts from it Drive a real browser. Click, type, screenshot. How the desktop works https://withruntime.com/docs/python previews-and-the-desktop Pause it. Fork it. Snapshot it. Plug it in. All from the same sandbox. Everything you need, built in. Secure by design. Every sandbox is its own machine. Security and compliance https://withruntime.com/docs/security Switch by changing one import. 1. python from e2b import Sandbox Your code written for E2B, Daytona, Vercel Sandbox, Blaxel 2. python - from e2b import Sandbox+ from withruntime.e2b import Sandbox One import the only line that changes 3. bash $ pip install withruntime Install Python or JavaScript 4. up to 5× less Save money for the same 1,000 sandbox hours Switch guide https://withruntime.com/docs/migrate Questions before you switch. Why is it so much cheaper? E2B and Daytona bill every vCPU a sandbox holds for as long as it runs. Runtime bills the CPU your code uses, $0.025 per active vCPU-hour above a default floor of a twentieth of a vCPU, and $0.0075 per GiB-hour of memory, the lowest memory rate of the providers we compare that price memory on its own. There is no plan fee. Time spent waiting on a model costs only memory and that floor, so the same agent job costs 42% to 88% less than at fourteen other providers. See the pricing. https://withruntime.com/pricing What does an idle sandbox cost? Only its paused storage. A sandbox pauses itself after 60 seconds with nothing happening in it: no request, no running command, no open connection, no traffic and no CPU use. It keeps its memory, files and processes for $0.08 per GB a month, and the next request wakes it, running its next command 153 ms later, timed on Runtime's servers. See idle and paused costs. https://withruntime.com/docs/pricing Do I have to rewrite my code? No. Code written for E2B, Daytona, Vercel Sandbox or Blaxel runs by changing one import, in JavaScript and Python. Or paste the agent prompt into your coding agent: it switches the project on a branch, tests it on the included usage and tells you what you save. Read the switch guide. https://withruntime.com/docs/migrate What is included every month? 100 hours of a 2 vCPU, 4 GB sandbox: 400 GiB-hours of memory and 100 vCPU-hours of active CPU, no credit card, renewed on the 1st. Without credit, up to eight sandboxes at once with 2 vCPUs and 4 GiB each. Past it, prepaid credit from $10, with no plan fee, and your first top-up within 30 days of signing up is matched with credit, up to $1,000. See what is included. https://withruntime.com/docs/included-usage How fast does a sandbox start? Timed on Runtime's servers in Virginia on 28 September 2026, the API's own time for each request: a new sandbox 2 vCPUs, 4 GiB RAM, 4 GiB disk is running 102 ms after the create request arrives 262 ms at p99 and has run its first Python command 221 ms after it, across 100 sequential starts with no errors. From a laptop in the US Mountain time zone, network included, the first Python result came 331 ms after the create request at the median 465 ms p95, 28 September 2026 . On the server, a paused sandbox is running again 76 ms after the wake request and has run its next command 153 ms after it; from the same laptop, its next command came 569 ms after the call 28 September 2026 . See the measurements. https://withruntime.com/docs/speed How is each sandbox isolated? Every sandbox is a Firecracker microVM with its own Linux kernel, disk and guest environment, on dedicated servers Runtime operates. CPU, memory, network rules and time limits are enforced on the host, outside the guest. Read the security model. https://withruntime.com/docs/security Is there an uptime promise? Yes. Paid accounts are promised 99% API uptime every calendar month, measured from outside our servers and published on the status page. If a month falls short, 10% of that month's charges comes back as credit automatically, with no claim to file. Read the Uptime Promise. https://withruntime.com/legal/sla How big, and for how long? A paid sandbox takes up to 16 vCPUs and 64 GiB of memory, and an account runs up to 100 at once from its first top-up. A sandbox runs while it works and pauses itself when idle; there is no time limit unless you set one. See the sizes. https://withruntime.com/docs/pricing how-many-at-once All the docs https://withruntime.com/docs 400 sandbox hours,every month. Hours of a 1 GB sandbox, included free. - No credit card - Eight sandboxes at once, 2 vCPU and 4 GiB each - Then prepaid credit from $10, no plan fee Start free, no card https://withruntime.com/account