Modal vs Agent 37
Modal runs short-lived sandboxes next to GPUs, built for big bursts of jobs that end within 24 hours. Your code carries work forward with filesystem snapshots. Agent 37 gives each agent its own instance that stays around, sleeps when idle and wakes with its memory kept.
The companies and products
Modal
Modal is a serverless cloud for AI work: inference, training, batch jobs and sandboxed code, all driven from Python, TypeScript or Go code.
Modal Sandboxes are containers you create from code, run commands in, and then terminate. By default they run under gVisor, a user-space kernel from Google. Since October 2026 you can also pick a VM runtime with its own Linux kernel for Docker and FUSE (Battleships tracks that as a separate card, Modal VM Sandboxes). Your code can save a sandbox's disk as a filesystem snapshot and start new sandboxes from it. It suits teams that already run models on Modal and want scalable code execution next to their GPUs.
Agent 37
Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.
You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor. A VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.
Which use cases each one fits
For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “15th cheapest of 336” means 14 of the other 335 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.
| Use case and its workload | Modal: price rank | Agent 37: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Agent 37 ranks #4 at $551 a month and boat #5 at $634. Modal's default gVisor sandbox is a compromise at $633, because Docker needs the VM runtime; Modal VM Sandboxes rank #27 at $633. | 106th of 365, with limits $633 a month | 4th cheapest of 365 $551 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 ranks #1 here at $279 a month: its instances sleep when idle and keep their memory. Modal is a compromise at $1,574, because your code snapshots the filesystem and starts a new sandbox at least once a day. boat ranks #6 at $657. | 61st of 361, with limits $1,574 a month | Cheapest of 361 $279 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Agent 37 ranks #1 at $22 a month and Modal #15 at $140 for short code runs. boat is a compromise here because its start limits slow large bursts of short jobs. | 15th cheapest of 336 $140 a month | Cheapest of 336 $22 a month | 189th of 336, with limits $2,000 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Agent 37 ranks #1 at $79 a month, boat #3 at $209 and Modal #18 at $671. Agent 37 runs up to 1,000 awake instances once you have topped up $1,000. | 18th cheapest of 349 $671 a month | Cheapest of 349 $79 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month Modal ranks #6 here as a full match, with no per-start fee. Agent 37 and boat are compromises: Agent 37's default type shares its vCPUs, and boat limits starts per plan. | 6th cheapest of 349 $11,982 a month | 9th of 349, with limits $363 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 62nd cheapest of 359 $889 a month | Cheapest of 359 $58 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month boat ranks #2 at $86 a month and Modal #110 at $1,112, with Docker on its VM runtime. Agent 37 is a compromise here: Docker needs its VM type, at 2.5x its default compute rate. | 110th cheapest of 374 $1,112 a month | 227th of 374, with limits $96 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 129th of 371, with limits $9.07 a month | 3rd cheapest of 371 $12 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Agent 37 ranks #3 at $120 a month, boat #7 at $200 and Modal #45 at $153. On Agent 37 you build a noVNC template or use its Ubuntu VM template. On Modal its official example installs Xvfb, Chromium and noVNC in a VM sandbox. boat has a 60 fps desktop built in. | 45th cheapest of 367 $153 a month | 3rd cheapest of 367 $120 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 57th of 356, with limits $121 a month | 47th of 356, with limits $29 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 98th cheapest of 343 $252 a month | Cheapest of 343 $32 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 171st of 327, with limits $5,957 a month | 39th of 327, with limits $648 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 289th of 351, with limits $464 a month | Cheapest of 351 $43 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month Modal is the one of the three with GPUs, from T4 to B300. | 18th cheapest of 102 $1,116 a month | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Modal | Agent 37 | boat |
|---|---|---|---|
| Isolation | gVisor by default; VM runtime with its own kernel available | gVisor by default; full VM as an opt-in instance type | Every sandbox is a full VM with its own kernel |
| Docker inside | Yes with the VM runtime (runtime="vm"), at the same price; not documented on gVisor | Yes on the VM type, at 2.5x the default compute rate | Yes, in every sandbox |
| Nested virtualization | VM runtime only, Enterprise plan, as an experimental option | /dev/kvm on the VM type, with a ready Android template | /dev/kvm in every sandbox, Android emulator works |
| Longest session | 24 hours (default 5 minutes); for longer work, a filesystem snapshot and a new sandbox | No documented maximum; runs until stopped or put to sleep | No cap once auto-stop is off on a paid plan (default 1 hour, timer up to 30 days) |
| Idle and resume | No paused state; your code saves the root disk with a filesystem snapshot or a Volume, then starts a new sandbox from it | Opt-in auto-sleep after a quiet period, memory checkpointed, wakes on the next request | Stop with no compute charge, resume with your files and packages; memory is not saved, so a resume is like a reboot |
| Fork | One filesystem snapshot boots many new sandboxes; memory snapshots in alpha (they end the sandbox) | Fork any running, stopped or sleeping instance (disk copy, the fork boots fresh) | Fork a running sandbox from its last 1-minute snapshot (disk copy, the fork boots fresh) |
| Custom images | Build images in code or pull any linux/amd64 registry image | Your own linux/amd64 Docker image as a template | Start from boat's image or a saved snapshot; you cannot boot your own Docker image |
| GPUs | T4 to B300; 10 at once on Starter, 50 on Team | None | None |
| Desktop and computer use | You set it up: Modal's official example installs Xvfb, Chromium, x11vnc and noVNC in a VM sandbox | You set it up: noVNC desktop through a template build, or the Ubuntu VM template | 1920x1080, 60 fps desktop with Chrome and computer tools in every sandbox |
| Built-in coding agents | You install the harness in the image (official OpenCode example) | Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API per instance | Claude Code, Codex, pi, OpenCode, Prime Agent, Kimi Code, Mistral Vibe, with a prompt, steer and events API |
| Keys kept out of the sandbox | Secrets are environment variables, or you run your own proxy in a sidecar (beta) | Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars | Optional AI credentials proxy ($1 a day while on, plus $1 per 1,000 requests) for model providers and any HTTPS API you register |
| Outbound network rules | Block all, IP-range allowlist, domain allowlist (beta) | No outbound allowlist documented | No provider-side allowlist |
| Regions | US, EU and Asia-Pacific; pinning a region costs 1.15x to 1.75x | United States | Germany, Finland and France; no region choice; snapshot copies can be stored outside the EU |
| CPU speed (V8 Web Tooling, 4 vCPU / 8 GB, StarSling run of 3 October 2026) | VM runtime 15.48 runs/s, gVisor 12.60; measured with cpu=4 | Not in the public benchmarks we use | 28.06 runs/s on an AMD Ryzen 9 9950X host; boat does not promise a CPU model |
Every feature Battleships tracks (43)
| Feature | Modal | Agent 37 | boat |
|---|---|---|---|
| Full VM (own kernel) | No documented way | No documented way | Yes |
| Docker inside | No documented way | No documented way | Yes |
| Nested virtualization | No documented way | No documented way | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No documented way | Not published | Yes |
| Desktop GUI | With your own setup | With your own setup | Yes |
| Browser | With your own setup | Yes | Yes |
| Computer-use API | With your own setup | No documented way | Yes |
| SSH | With your own setup | Yes | Yes |
| Persistent disk | With your own setup | Yes | Yes |
| Pause/resume | No documented way | Yes | Yes |
| Automatic snapshots | No documented way | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Not published | Yes | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | No documented way | Yes | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | Yes | Not published | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | No documented way | Yes | Yes |
| Secret proxy for any API | No documented way | No documented way | Yes |
| Preinstalled agents | With your own setup | Yes | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | No documented way | No documented way | No documented way |
| GPU | Yes | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | No documented way | No documented way | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Not published | Yes | Yes |
| Audit logs | Yes | Not published | No documented way |
| SSO | Yes | No documented way | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Yes | No documented way | No documented way |
| EU data residency | Yes | No documented way | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's run of 3 October 2026 (run 37073680030), the V8 Web Tooling Benchmark at 4 vCPU / 8 GB did 28.06 runs/s on boat, 15.48 on Modal's VM runtime and 12.60 on Modal gVisor. StarSling ran Modal with cpu=4, and the sandbox saw 4 CPUs (PR #121). Every boat sandbox in that run ran on an AMD Ryzen 9 9950X host; boat also places some sandboxes on other hosts, and does not promise a CPU model. Providers ran on different hardware in different regions. Agent 37 is not in the public benchmarks we use, so we cannot say how it compares. Its default instances share host resources, and its Performance type runs on dedicated cores.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Modal measured on: Sandbox (gVisor), request = size, any region. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Agent 37 is not in the public benchmarks we use, so we cannot say which is faster.
Pricing in five scenarios
Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | Modal, a month | Agent 37, a month | boat, a month |
|---|---|---|---|
| One coding agent, workdays 4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days | $0 · Starter | $6 · Wallet (any top-up) | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $109 · Starter · with limits | $12 · Wallet (any top-up) | $26 · $20/mo |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $1,480 · Starter · with limits | $329 · Wallet ($50 lifetime top-ups) | $317 · $20/mo × 3 seats |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $579 · Team | $33 · Wallet ($1,000 lifetime top-ups) | $200 · $100/mo × 2 seats |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $1,911 · Team · with limits | $73 · Wallet ($1,000 lifetime top-ups) · with limits | $8,800 · $2000/mo · with limits |
Modal: Modal bills by the second for whichever is higher, the CPU and memory you request or what you use, and an idle sandbox pays until it is terminated. Modal prices CPU per physical core, and one core equals 2 vCPU, so 4 vCPU / 8 GiB costs $0.476 an hour at a full request. StarSling ran Modal with cpu=4 (PR #121); sized that way, Modal bills 4 cores, $0.76 an hour. Starter is free with $30 of monthly credit, and Team is $250 a month with $100 of credit.
Agent 37: Agent 37 uses a prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while asleep. Performance compute costs 4x and VM compute 2.5x the default rate.
Agent 37: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, with 51 GB of disk included. A stopped sandbox has no compute charge. Saved snapshots above the plan's count ($0.056 a day each) and the optional AI credentials proxy still charge while sandboxes are stopped. Starts above the plan's included number cost $0.03 to $0.07 each.
Limits in those scenarios
On Modal a sandbox lives at most 24 hours. Its root disk ends with it, so the workday, always-on and fleet scenarios keep only files your code saves to a filesystem snapshot or a Volume. The 50-agent fleet needs Docker, which the default gVisor sandbox does not document, so it does not fit there; Modal VM Sandboxes run it. Agent 37 caps awake instances by total top-ups, up to 1,000 at $1,000, and its egress price is not published. Its default type shares vCPUs, so the 1,000-job burst is marked a compromise there. On boat, the $2,000 plan includes 90 starts a minute and 2,400 a day; extra starts cost $0.03 to $0.07, and starts above 270 a minute fail with 429. So the 1,000-job burst does not fit on boat.
| Scenario | Modal | Agent 37 | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario |
| None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel |
|
| None for this scenario |
| Sandboxes for your users | None for this scenario |
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Modal when
your sandboxes need GPUs, must run outside the US and Europe, need an outbound allowlist, or are huge bursts of short jobs that finish in minutes.
- GPUs next to your sandboxes. If your agent trains or runs models, Modal rents GPUs from T4 to B300 on the same platform as its sandboxes.
- Regions and outbound rules. Modal runs in the US, EU and Asia-Pacific, and can block a sandbox's outbound traffic or allow only chosen domains.
- Very large bursts of short jobs. For huge fleets of short sandboxes, Modal runs up to 5,000 containers on Team, and memory snapshots are in alpha.
Use Agent 37 when
you host one mostly idle assistant per customer in the US that should sleep with its memory kept and wake on the next message.
- Sleeps when idle and keeps its memory. For assistants that wait most of the day, an Agent 37 instance sleeps, keeps its memory and wakes on the next message.
- No 24-hour cutoff. An Agent 37 instance has no documented maximum lifetime, so an always-on agent keeps running until you stop it.
- Lowest bills of the three in most scenarios. Agent 37's default type costs about $0.012 an hour in compute at 4 vCPU / 8 GB, and its bill is lowest of the three in three of our five scenarios.
Where boat fits
Modal is built for short jobs and Agent 37 for mostly idle assistants. If your agents do hours of real work, with installs, builds, Docker and a browser, boat gives each one a full VM by default. It saves the disk every minute, forks while it runs, and has no session cap once auto-stop is off on a paid plan.
Docker and systemd in every sandbox
Both default to gVisor. Docker on Modal needs the VM runtime, at the same price. Docker on Agent 37 needs its VM type, which bills compute at 2.5x and has no init system, so you start services from your entrypoint. Every boat sandbox has Docker and systemd.
A disk saved with no code
On Modal your code snapshots the filesystem before the 24-hour limit and boots a new sandbox from it. Agent 37 backs up nightly, plus one on-demand slot. boat saves the disk every minute and at each stop. Writes from the last minute or so can be missing after a machine failure.
Keys stay outside, for any API
On Modal secrets are environment variables unless you run your own sidecar proxy. Agent 37 keeps its managed models, search and Composio keys outside. boat's optional paid proxy covers supported model providers and any HTTPS API you register.
Use boat when your agents work for hours or days: installs, builds, tests, Docker and a desktop on a full VM by default, with the disk saved every minute, fork while running and keys kept outside for any API. Compare it one to one: boat vs Modal and boat vs Agent 37.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is Modal cheaper than Agent 37?
No, in most of our scenarios Agent 37 is far lower. One always-on agent costs $12 a month on Agent 37, against $109 on Modal, which also needs a new sandbox each day. 300 user sandboxes cost $33 against $579. One agent on workdays costs $0 on Modal inside its $30 Starter credit, against $6 on Agent 37. boat costs $26, $200 and $20 for those three.
Which is faster, Modal or Agent 37?
We cannot say: Agent 37 is not in the public benchmarks we use. In StarSling's run of 3 October 2026, Modal's VM runtime did 15.48 runs/s and its gVisor runtime 12.60 on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB. boat did 28.06 on an AMD Ryzen 9 9950X host.
Can Modal or Agent 37 run Docker?
Both on their VM options. Modal runs Docker with runtime="vm", at the same price as gVisor. Agent 37 runs it on its VM type, which bills compute at 2.5x the default rate. Every boat sandbox runs Docker with no extra setting.
How long can a session run on Modal and on Agent 37?
A Modal sandbox has a default timeout of 5 minutes and a maximum of 24 hours; for longer work, Modal recommends a filesystem snapshot and a new sandbox. An Agent 37 instance has no documented maximum and runs until you stop it or it sleeps on idle. On boat, auto-stop defaults to 1 hour; turn it off on a paid plan for no session cap.
Do Modal or Agent 37 have GPUs?
Modal does, from T4 up to B300, on its default gVisor runtime. Agent 37 and boat are CPU machines.
Where do Modal and Agent 37 run?
Modal runs in the US, the EU and Asia-Pacific, and you can pin a region for 1.15x to 1.75x the price. Agent 37 runs on dedicated servers in the United States. boat runs on machines in Germany, Finland and France, and you cannot pick a region.
Try boat
Install the CLI, then run boat new.
7-day free trial