Koyeb vs OpenAI Containers
A Koyeb sandbox is a microVM you start from any Docker image, expose on a port and can put to sleep. An OpenAI container is a tool inside OpenAI's model API. The model runs Python or shell there on a fixed image. By default the box expires after 20 minutes without use, and the create call can set a longer idle time.
The companies and products
Koyeb
Koyeb is a serverless cloud for apps, inference and sandboxes. In February 2026 it agreed to join Mistral AI.
A Koyeb sandbox is a Koyeb service: a microVM that starts from any Docker image. You drive it from Python or JavaScript SDKs or the Koyeb CLI: run commands, read files, expose a port and take snapshots. The default image comes with four coding agents. A sandbox can scale to zero when idle and wake on the next request, on CPU or GPU instance types. It suits teams that run AI agents or untrusted code next to apps they already host on Koyeb.
OpenAI Containers
OpenAI Containers are the sandboxes OpenAI runs for its own model tools: Code Interpreter, Hosted Shell and the Agents API's hosted sandbox.
This is a different kind of product from boat: a tool inside OpenAI's model API, not a machine you rent. You create a container through the API, or a Responses call makes one. The model runs Python or shell commands in it on a fixed Debian 12 image without sudo. By default the container expires after 20 minutes without use; the create call can set a different idle time. It is built for apps that already call OpenAI models and want them to run code, read files and make charts without running any servers.
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. “6th cheapest of 336” means 5 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 | Koyeb: price rank | OpenAI Containers: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs Docker, root and a disk that survives. Hosted OpenAI containers run without sudo and document no Docker; you can connect the Agents API to a sandbox you host. Koyeb does not document Docker inside, and you keep files with SDK snapshots or a small volume. boat runs Docker and saves its disk with no code. | 92nd of 365, with limits $366 a month | 357th of 365, with limits $17,371 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month needs its files to stay. An OpenAI container discards its data when it expires. On Koyeb, keep the sandbox awake or take an SDK snapshot before Deep Sleep. On boat, turn auto-stop off on a paid plan. | 194th of 361, with limits $923 a month | 344th of 361, with limits $13,140 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 This is what OpenAI Containers are built for: the model writes code and runs it in the same API call, with no machine to manage. Koyeb also fits short code runs well, with small instances that scale to zero and wake on the next request. | 6th cheapest of 336 $66 a month | 198th of 336, with limits $6,000 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 Koyeb gives each user an HTTPS port and wakes a sleeping sandbox on request. OpenAI documents no inbound ports for hosted containers. boat gives each sandbox up to 50 HTTPS URLs and SSH. | 8th cheapest of 349 $495 a month | 349th of 349, with limits $3,780 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 | 233rd of 349, with limits $1,631 a month | 195th of 349, with limits $30,000 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 | 27th cheapest of 359 $429 a month | 355th of 359, with limits $5,760 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 CI needs Docker, root and open internet. Hosted OpenAI containers document no Docker or root, and Code Interpreter has no outbound access until an admin allows domains. Koyeb documents neither Docker inside nor /dev/kvm. boat has all of them. | 143rd of 374, with limits $88 a month | 347th of 374, with limits $1,728 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box you keep all month needs SSH and a disk that stays. Koyeb runs commands through its SDKs and CLI. Hosted OpenAI containers document no SSH, and their files go when they expire. A boat sandbox has SSH and a disk saved every minute. | 232nd of 371, with limits $37 a month | 365th of 371, with limits $1,051 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 OpenAI has a hosted browser for computer use in its Agents API beta. On Koyeb you add a desktop and VNC to your own Docker image. boat streams a 60 fps desktop with Chrome. | 128th of 367, with limits $123 a month | 353rd of 367, with limits $5,280 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 | 237th of 356, with limits $123 a month | 335th of 356, with limits $1,440 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 | 242nd of 343, with limits $89 a month | 334th of 343, with limits $1,755 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 | 67th of 327, with limits $1,683 a month | 307th of 327, with limits $35,100 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 | 261st of 351, with limits $299 a month | 310th of 351, with limits $870 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 Koyeb runs GPU instances from an RTX 4000 SFF Ada up to H100, H200 and B200. OpenAI containers and boat have no GPUs. | 3rd cheapest of 102 $628 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 | Koyeb | OpenAI Containers | boat |
|---|---|---|---|
| What it is | A sandbox service you start from any Docker image and drive with SDKs or the Koyeb CLI | A sandbox tool the model uses inside OpenAI's API | A cloud VM you create, keep, stop and reach from outside |
| Isolation | Cloud Hypervisor microVM per instance | A fully sandboxed virtual machine; hypervisor not named | Full VM with its own kernel, on AMD Ryzen 7 9700X and Ryzen 9 9950X hosts dedicated to boat; vCPUs are shared |
| Docker, root and nested virtualization | Starts from any Docker image; Docker inside and /dev/kvm not documented | Commands do not run with sudo on a fixed Debian 12 image; Docker and /dev/kvm not documented. You can connect the Agents API to a self-hosted sandbox | Root, systemd, Docker and /dev/kvm on every sandbox |
| Machine size | Instance types up to 40 vCPU / 128 GB, and GPU types larger still | 1, 4, 16 or 64 GB of memory; vCPU not published. Agents API sandboxes: 1 vCPU / 1 GB, 2 vCPU / 4 GB or 4 vCPU / 16 GB | 4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB (xlarge needs the $100 plan) |
| Files after the session | Local disk is lost on redeploy and in Deep Sleep. You set it up: SDK snapshots save the filesystem; volumes (preview, 1 to 10 GB, not on eco instances) persist | Data is discarded when the container expires. Agents API publishes files in /workspace/outputs as downloadable artifacts | Disk saved every minute and at each stop, with no code; a stopped disk is kept at least 14 days |
| Lifetime and sleep | No forced session cap; scales to zero after an idle period (5 minutes minimum) and wakes on the next request | By default expires after 20 minutes without use (expires_after can be set; no maximum published); Agents API sandboxes can be deleted after an hour without activity | No cap once auto-stop is off on a paid plan; auto-stop defaults to 1 hour, up to 30 days |
| Snapshots and fork | SDK snapshots of the filesystem, or with running processes, then new sandboxes from a snapshot | No fork call documented. You set it up: create a new container and upload the same files | Fork a running sandbox from its last 1-minute snapshot |
| Inbound access | One exposed HTTPS port at a time, plus an optional TCP proxy to one port (preview) | No inbound ports documented for hosted containers; you reach them through the API | Up to 50 HTTPS URLs, token-protected by default; SSH; raw ports over IPv6 only on sandboxes with no IPv4 of their own |
| Outbound internet | Open by default; can block all outbound traffic or allow only listed IPs and CIDRs | Code Interpreter and Hosted Shell: off until an admin sets an org domain allowlist. Agents API sandboxes: on by default, can be limited to 1 to 100 hosts | Open internet; no provider-side allowlist |
| Keeping API keys out of the sandbox | Secrets are set as environment variables inside the service | domain_secrets: a sidecar adds the real header for approved domains; the model sees a placeholder | Optional paid proxy ($1 a day plus $1 per 1,000 requests) for model providers and custom HTTPS APIs; other secrets still enter the sandbox |
| Coding agents | Default image preinstalls Mistral Vibe, Codex, Gemini and OpenCode, run through the command API; no prompt or steer API | Agents API (beta) drives a managed Codex harness from outside, with steering, events and webhooks | Seven harnesses installed, including Claude Code, Codex and OpenCode, with a prompt, steer and events API |
| Desktop and computer use | No desktop or browser preinstalled; you can add them to a custom Docker image | Hosted browser for the Agents API computer_use tool | 1920x1080, 60 fps desktop and Chrome, computer tools for agents, embeddable stream |
| GPUs | RTX 4000 SFF Ada up to H100, H200 and B200, and multi-GPU | None | None |
| Regions | Frankfurt, Paris, Washington D.C., Singapore, Tokyo and more; you pick the region | US or EU processing for Code Interpreter; Agents API data residency in the US only | Germany, Finland and France; no region choice, no US or Asia region |
Every feature Battleships tracks (43)
| Feature | Koyeb | OpenAI Containers | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | No documented way | Yes |
| Nested virtualization | No documented way | No documented way | Yes |
| Root | Not published | No documented way | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No documented way | Yes | Yes |
| Browser | No documented way | Yes | Yes |
| Computer-use API | No documented way | Yes | Yes |
| SSH | No documented way | No documented way | Yes |
| Persistent disk | With your own setup | No documented way | Yes |
| Pause/resume | Yes | No documented way | Yes |
| Automatic snapshots | Yes | No documented way | Yes |
| Fork/clone | Yes | No documented way | Yes |
| Live fork (no pause) | Not published | No documented way | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | No documented way | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | No documented way | No documented way |
| HTTPS preview URLs | Yes | No documented way | Yes |
| Raw TCP inbound | Yes | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | Yes | No documented way |
| Secret proxy | No documented way | Yes | Yes |
| Secret proxy for any API | No documented way | Yes | Yes |
| Preinstalled agents | Yes | No documented way | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | Yes | 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 | Yes | Yes | No documented way |
| BYOC | Yes | 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 | No documented way | Not published | Yes |
| Usage per sandbox (API) | No documented way | No documented way | Yes |
| Audit logs | Yes | Not published | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | No documented way | Yes | No documented way |
| EU data residency | Yes | Yes | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Koyeb nor OpenAI Containers is in the public benchmarks we use, so we cannot say which is faster. OpenAI does not publish the vCPU behind each container size. Koyeb publishes a CPU share of at least 0.25 dedicated vCPU per GB of memory, bursting to all cores. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. 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.
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. 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. Koyeb and OpenAI Containers are 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 | Koyeb, a month | OpenAI Containers, 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 | $29 · Pro | $228 · API pay as you go · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $57 · Pro | $1,051 · API pay as you go · with limits | $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 | $475 · Pro · with limits | $11,405 · API pay as you go · with limits | $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 | $329 · Scale | $1,620 · API pay as you go · with limits | $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 | $485 · Scale · with limits | $6,000 · API pay as you go · with limits | $8,800 · $2000/mo · with limits |
Koyeb: Koyeb bills each instance per second at a fixed price per instance type: eco-xlarge (4 vCPU / 8 GB, 20 GB disk) costs $0.0576 an hour. Deep Sleep costs nothing. Pro costs $29 a month with $10 of usage included, and Scale $299 with $100 included; the rest of the fee is not credit.
OpenAI Containers: OpenAI bills each container session by the minute for the memory size you pick, with a 5-minute minimum, and model tokens are billed on top. There is no plan fee. The scenarios use the 16 GB size ($1.44 an hour) for 8 GB needs, because OpenAI does not publish the vCPU per size.
OpenAI Containers: 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, per second while it runs. The $20 plan includes 12 starts a minute, 60 an hour and 200 a day; extra starts cost $0.03 to $0.07. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; extra saved snapshots and the AI credentials proxy still charge.
Limits in those scenarios
OpenAI Containers do not fit any of the five scenarios as written. Hosted containers discard their files when they expire, document no Docker or root, and do not publish the vCPU per size. Code Interpreter and Hosted Shell containers have no outbound access until an admin allows domains. Koyeb's priced shape for 4 vCPU / 8 GB is eco-xlarge, with a 20 GB local disk that takes no volume, and Koyeb does not document Docker inside, so the 50-agent fleet is marked as not fitting. At 1,000 short jobs at once nothing fits as priced: OpenAI's concurrency is not published, and boat's $2,000 plan includes 90 starts a minute and refuses starts above 270 a minute.
| Scenario | Koyeb | OpenAI Containers | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| 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 Koyeb when
you want sandboxes from your own Docker images that sleep when idle, wake on a request, use GPUs or run in the US or Asia.
- A machine you control. Good when you want to pick the image, the size and the port yourself: Koyeb starts any Docker image as a microVM.
- GPUs and wake on request. Useful when sandboxes need a GPU, or sit idle and must wake on the next request, in about 200 ms with Light Sleep (preview).
- Many regions. Good for sandboxes that must run in the US or Asia: Koyeb runs in Washington D.C., Singapore, Tokyo and Europe.
Use OpenAI Containers when
your app already calls OpenAI models and the model only needs to run short pieces of code or shell commands on files you give it.
- Built into the model call. Useful if your app already calls OpenAI models: one tool line in a request gives the model a place to run code.
- Nothing to run or clean up. Good for short code runs: OpenAI creates the container, bills it by the minute and lets it expire on its own.
- Locked-down network by default. Useful if code must reach only chosen domains, with keys for those domains added by a sidecar the model cannot read.
Where boat fits
If you run coding agents that work for hours, look at boat. Koyeb gives you a machine you shape yourself, and OpenAI Containers give the model a short-lived box with no root. boat gives each agent a full VM that saves its disk, with agents, a desktop and hosting built in. boat has no GPU and no US or Asia region, and it caps starts per plan.
A disk saved with no code
An OpenAI container discards its files when it expires. On Koyeb you keep files with SDK snapshots or a preview volume of 1 to 10 GB. boat saves the disk every minute and at each stop, and keeps a stopped disk for at least 14 days.
Root, Docker and /dev/kvm
OpenAI runs hosted commands without sudo and documents no Docker. Koyeb documents neither Docker inside a sandbox nor /dev/kvm. boat has root, systemd, Docker and /dev/kvm on every sandbox.
Agents and ports built in
On Koyeb you run agents through the command API and expose one port at a time. OpenAI's Agents API drives its own Codex harness, and hosted containers take no inbound connections. boat installs seven coding agents you drive from outside, with up to 50 HTTPS URLs and a 60 fps desktop.
Use boat when your agents need a real machine they keep: root, Docker, /dev/kvm, a disk saved every minute, open internet and ports you can reach, with seven coding agents installed. Compare it one to one: boat vs Koyeb and boat vs OpenAI Containers.
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 Koyeb cheaper than OpenAI Containers?
In the scenarios on this page, at list prices, yes. One agent on workdays costs $29 a month on Koyeb against $228 on OpenAI. One agent running all month costs about $42 of Koyeb compute plus the $29 Pro fee ($10 included), against $1,051 on OpenAI. boat costs $20 and $26. OpenAI is priced at its 16 GB size, bills model tokens on top, and does not fit these scenarios as written. For a few short code runs a month, OpenAI has no plan fee and can cost less.
Which is faster?
Neither Koyeb nor OpenAI Containers is in the public benchmarks we use, so we cannot say. boat did 28.06 runs/s on the V8 Web Tooling Benchmark in StarSling's run of 3 October 2026, on a Ryzen 9 9950X host.
Can I run Docker in Koyeb or OpenAI Containers?
Koyeb sandboxes start from Docker images, but Koyeb does not document Docker inside a sandbox. OpenAI's docs say hosted commands do not run with sudo and document no Docker; you can connect the Agents API to a sandbox you host. boat has root, systemd, Docker and /dev/kvm on every sandbox.
Do they keep files between sessions?
An OpenAI container discards its data when it expires, by default after 20 minutes without use. On Koyeb you keep files with SDK snapshots or a preview volume of 1 to 10 GB. A boat sandbox saves its disk every minute and at each stop, and keeps a stopped disk for at least 14 days.
Can I open a web app running inside the sandbox?
On Koyeb you can expose one HTTPS port at a time. OpenAI documents no ports, URLs or SSH for hosted containers. boat gives each sandbox up to 50 HTTPS URLs, token-protected by default, and SSH.
Is boat SOC 2 compliant?
SOC 2 is in progress. OpenAI's API Platform is audited for SOC 2 Type 2, and Koyeb lists ISO 27001 and SOC 2 on its Enterprise plan. Live status is at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Try boat
Install the CLI, then run boat new.
7-day free trial