{
"category": "agent-sandboxes",
"rows": [
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.0162",
"cost_usd": 0.0162,
"exact_shape": true,
"fleet": "≥ $142.56",
"fleet_plan": "Pro 5x",
"fleet_usd": 142.56,
"light": "≥ $0.0162",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.0162",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/ci-runners/",
"label": "CI runners",
"slug": "ci-runners"
},
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/lizard/",
"logo": "/logos/lizard.png",
"logo_dark": false,
"name": "Lizard",
"operator": "Lizard",
"plate": 31,
"slug": "lizard",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Firecracker microVM sandboxes for AI agents in three fixed sizes billed per second while running, plus GitHub Actions runners at the same rates, on a $19 monthly plan that includes $19 of usage."
},
"rank": 1,
"shape": "Small (2 vCPU / 4 GB)",
"src": 1,
"terms": {
"at_once": {
"text": "20"
},
"pay": {
"detail": "A monthly plan from $19/mo that includes usage; more usage costs extra.",
"key": "subscription",
"label": "Plan from $19/mo"
},
"starts": {
"detail": "Sandbox starts (create, resume, fork) allowed: 24/min · 120/h · 400/day, then refused.",
"over": "then refused",
"text": "24/min · 120/h · 400/day"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.017",
"cost_usd": 0.017,
"exact_shape": true,
"fleet": "≥ $149.60",
"fleet_plan": null,
"fleet_usd": 149.60000000000002,
"light": "≥ $0.017",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.017",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/instabox/",
"logo": "/logos/instabox.svg",
"logo_dark": false,
"name": "InstaBox",
"operator": "InstaBox",
"plate": 26,
"slug": "instabox",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Firecracker microVM machines for agents with a desktop, Docker and coding agents preinstalled, billed per second for vCPU and memory on top of a monthly plan."
},
"rank": 2,
"shape": "2 vCPU / 4 GB",
"src": 2,
"terms": {
"at_once": {
"text": "100"
},
"pay": {
"detail": "A monthly plan from $20/mo that includes usage; more usage costs extra.",
"key": "subscription",
"label": "Plan from $20/mo"
},
"starts": {
"detail": "Sandbox starts (create, resume, fork) allowed: 10/min, then refused.",
"over": "then refused",
"text": "10/min"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.018",
"cost_usd": 0.018,
"exact_shape": true,
"fleet": "≥ $158.40",
"fleet_plan": null,
"fleet_usd": 158.39999999999998,
"light": "≥ $0.018",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.018",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/ci-runners/",
"label": "CI runners",
"slug": "ci-runners"
},
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/boat/",
"logo": "/logos/boat.svg",
"logo_dark": false,
"name": "boat",
"operator": "boat",
"plate": 6,
"slug": "boat",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Full-VM sandboxes for coding agents on a monthly plan, plus hosted GitHub Actions runners on the same machines."
},
"rank": 3,
"shape": "small (2 vCPU / 4 GB)",
"src": 3,
"terms": {
"at_once": {
"text": "100"
},
"pay": {
"detail": "A monthly plan from $20/mo that includes usage; more usage costs extra.",
"key": "subscription",
"label": "Plan from $20/mo"
},
"starts": {
"detail": "Sandbox starts (create, resume, fork) allowed: 12/min · 60/h · 200/day, then from $0.03 each.",
"over": "then from $0.03 each",
"text": "12/min · 60/h · 200/day"
}
},
"vt": true
},
{
"basis": "Flat price per size",
"caveats": [],
"cost": "≥ $0.03",
"cost_usd": 0.030000000000000002,
"exact_shape": true,
"fleet": null,
"fleet_plan": null,
"fleet_usd": null,
"light": "≥ $0.03",
"light_lower": false,
"lower_bound": true,
"notes": [
"rounding",
"minimum"
],
"per_hour": "$0.03",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/ci-runners/",
"label": "CI runners",
"slug": "ci-runners"
},
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/celesto/",
"logo": "/logos/celesto.png",
"logo_dark": false,
"name": "Celesto",
"operator": "Celesto AI, Inc.",
"plate": 10,
"slug": "celesto",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "MicroVM \"agent computers\" sold as agent sandboxes and as self-hosted-label runners for GitHub Actions, paid from prepaid credit."
},
"rank": 4,
"shape": "Standard (2 vCPU / 4 GB)",
"src": 4,
"terms": {
"at_once": {
"text": "10"
},
"pay": {
"detail": "You buy credit up front, then use it. Whether unused credit expires is not published.",
"key": "prepaid",
"label": "Prepaid credit"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Active CPU",
"caveats": [
{
"detail": "Only CPU in use is billed, so idle time costs less; the light-use column shows how much.",
"key": "active-cpu",
"label": "Active-CPU billing"
}
],
"cost": "≥ $0.1",
"cost_usd": 0.1,
"exact_shape": true,
"fleet": "≥ $880.00",
"fleet_plan": null,
"fleet_usd": 880.0,
"light": "≥ $0.01",
"light_lower": true,
"lower_bound": true,
"notes": [
"rounding",
"minimum"
],
"per_hour": "$0.1",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/upstash-box/",
"logo": "/logos/upstash-box.png",
"logo_dark": false,
"name": "Upstash Box",
"operator": "Upstash, Inc.",
"plate": 45,
"slug": "upstash-box",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Container sandboxes with Claude Code, Codex, OpenCode or Cursor built in, billed per active CPU hour by size, with fixed monthly keep-alive boxes."
},
"rank": 5,
"shape": "Small (2 vCPU / 4 GB)",
"src": 5,
"terms": {
"at_once": {
"text": "1,000"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.117",
"cost_usd": 0.11664,
"exact_shape": true,
"fleet": "≥ $1,026",
"fleet_plan": null,
"fleet_usd": 1026.432,
"light": "≥ $0.117",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.117",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/novita/",
"logo": "/logos/novita.png",
"logo_dark": false,
"name": "Novita AI",
"operator": "Novita AI",
"plate": 36,
"slug": "novita",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Agent sandboxes with pause/resume, memory snapshots and VNC desktops, billed per second per allocated vCPU and GiB of memory."
},
"rank": 6,
"shape": "2 vCPU / 4 GB",
"src": 6,
"terms": {
"at_once": {
"text": "100"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Active CPU",
"caveats": [
{
"detail": "Only CPU in use is billed, so idle time costs less; the light-use column shows how much.",
"key": "active-cpu",
"label": "Active-CPU billing"
}
],
"cost": "$0.15",
"cost_usd": 0.15,
"exact_shape": true,
"fleet": "$1,320",
"fleet_plan": null,
"fleet_usd": 1320.0,
"light": "$0.0654",
"light_lower": true,
"lower_bound": false,
"notes": [],
"per_hour": "$0.15",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/ci-runners/",
"label": "CI runners",
"slug": "ci-runners"
},
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/boxd/",
"logo": "/logos/boxd.svg",
"logo_dark": true,
"name": "boxd",
"operator": "Azin Tech Operating Company B.V.",
"plate": 7,
"slug": "boxd",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Persistent KVM Linux machines for agents and developers, driven by SDK, CLI or SSH, that fork and sleep with memory kept and bill per second on CPU time used, memory in use and disk written; plus a documented setup that runs GitHub-triggered CI on machines restored from a snapshot of the last green main run."
},
"rank": 7,
"shape": "2 vCPU / 4 GB",
"src": 7,
"terms": {
"at_once": {
"reason": "Machine quota, not a running limit, and boxd's pages disagree: 50 per organization (docs, FAQ; 2 without a payment method) vs 100 (pricing page); hibernated and stopped machines count",
"text": "?"
},
"pay": {
"detail": "You buy credit up front, then use it. Whether unused credit expires is not published.",
"key": "prepaid",
"label": "Prepaid credit"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.166",
"cost_usd": 0.1656,
"exact_shape": true,
"fleet": null,
"fleet_plan": null,
"fleet_usd": null,
"light": "≥ $0.166",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.166",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/blaxel/",
"logo": "/logos/blaxel.svg",
"logo_dark": false,
"name": "Blaxel",
"operator": "Blaxel, Inc. (part of Baseten)",
"plate": 5,
"slug": "blaxel",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Firecracker microVM sandboxes that drop to standby when idle and resume with memory intact, billed per GB of allocated memory per second while active, paid from prepaid credit."
},
"rank": 8,
"shape": "2 vCPU / 4 GB",
"src": 8,
"terms": {
"at_once": {
"text": "10"
},
"pay": {
"detail": "You buy credit up front, then use it. Unused credit expires.",
"key": "prepaid",
"label": "Prepaid credit"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.166",
"cost_usd": 0.1656,
"exact_shape": true,
"fleet": "≥ $1,457",
"fleet_plan": null,
"fleet_usd": 1457.28,
"light": "≥ $0.166",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.166",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/daytona/",
"logo": "/logos/daytona.png",
"logo_dark": false,
"name": "Daytona",
"operator": "Daytona Platforms Inc.",
"plate": 15,
"slug": "daytona",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "API-driven sandboxes for AI agents (Linux containers by default, Linux and Windows VMs, GPUs), billed per second for reserved vCPU, memory and disk."
},
"rank": 9,
"shape": "2 vCPU / 4 GB",
"src": 9,
"terms": {
"at_once": {
"reason": "No sandbox count; concurrency is bounded by the tier's pooled compute (Tier 1: 10 vCPU / 10-20 GiB RAM / 30 GiB disk)",
"text": "?"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "Sandbox starts (create, resume, fork) allowed: 300/min, then refused.",
"over": "then refused",
"text": "300/min"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [
{
"detail": "A sandbox is stopped after 1 h.",
"key": "session-cap",
"label": "Max session 1 h"
}
],
"cost": "≥ $0.166",
"cost_usd": 0.1656,
"exact_shape": true,
"fleet": "≥ $1,607",
"fleet_plan": "Pro",
"fleet_usd": 1607.28,
"light": "≥ $0.166",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.166",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/e2b/",
"logo": "/logos/e2b.png",
"logo_dark": false,
"name": "E2B",
"operator": "E2B",
"plate": 18,
"slug": "e2b",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Firecracker microVM sandboxes for AI agents, billed per second for the CPU and memory you provision."
},
"rank": 10,
"shape": "2 vCPU / 4 GB",
"src": 10,
"terms": {
"at_once": {
"text": "20"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "Sandbox starts (create, resume, fork) allowed: 60/min, then refused.",
"over": "then refused",
"text": "60/min"
}
},
"vt": true
},
{
"basis": "Active CPU",
"caveats": [
{
"detail": "Only CPU in use is billed, so idle time costs less; the light-use column shows how much.",
"key": "active-cpu",
"label": "Active-CPU billing"
}
],
"cost": "≥ $0.2",
"cost_usd": 0.2,
"exact_shape": true,
"fleet": "≥ $1,760",
"fleet_plan": null,
"fleet_usd": 1760.0,
"light": "≥ $0.074",
"light_lower": true,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.2",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/tensorlake/",
"logo": "/logos/tensorlake.svg",
"logo_dark": false,
"name": "Tensorlake",
"operator": "Tensorlake Inc.",
"plate": 42,
"slug": "tensorlake",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "MicroVM sandboxes for AI agents with suspend/resume, memory snapshots and clones, billed for active CPU plus allocated memory and disk from prepaid credit or a Pro plan."
},
"rank": 11,
"shape": "2 vCPU / 4 GB",
"src": 11,
"terms": {
"at_once": {
"text": "100"
},
"pay": {
"detail": "You buy credit up front, then use it. Whether unused credit expires is not published.",
"key": "prepaid",
"label": "Prepaid credit"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.206",
"cost_usd": 0.20600000000000002,
"exact_shape": true,
"fleet": "≥ $1,813",
"fleet_plan": null,
"fleet_usd": 1812.8000000000002,
"light": "≥ $0.206",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.206",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
}
],
"href": "/providers/google-agent-sandbox/",
"logo": "/logos/google-agent-sandbox.png",
"logo_dark": false,
"name": "Google Cloud Agent Platform sandboxes",
"operator": "Google LLC",
"plate": 25,
"slug": "google-agent-sandbox",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Managed sandboxes in Google Cloud's Gemini Enterprise Agent Platform (formerly Vertex AI Agent Engine) for code execution, shell, custom containers and computer use, billed per vCPU-hour and GiB-hour."
},
"rank": 12,
"shape": "2 vCPU / 4 GB",
"src": 12,
"terms": {
"at_once": {
"text": "1,000"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [
{
"detail": "A sandbox is stopped after 3 h.",
"key": "session-cap",
"label": "Max session 3 h"
}
],
"cost": "≥ $0.24",
"cost_usd": 0.24000000000000002,
"exact_shape": false,
"fleet": "≥ $2,362",
"fleet_plan": "Business",
"fleet_usd": 2362.0,
"light": "≥ $0.24",
"light_lower": false,
"lower_bound": true,
"notes": [
"minimum"
],
"per_hour": "$0.24",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/ci-runners/",
"label": "CI runners",
"slug": "ci-runners"
},
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/namespace/",
"logo": "/logos/namespace.svg",
"logo_dark": false,
"name": "Namespace",
"operator": "Namespace Labs",
"plate": 34,
"slug": "namespace",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Managed GitHub Actions runners on Linux (x64 and arm64), Windows and macOS, billed per minute by machine shape, with cache volumes and remote Docker builders."
},
"rank": 13,
"shape": "S (4 vCPU / 8 GB)",
"src": 13,
"terms": {
"at_once": {
"text": "3"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
},
{
"basis": "Running time",
"caveats": [],
"cost": "≥ $0.3",
"cost_usd": 0.30000000000000004,
"exact_shape": true,
"fleet": "≥ $2,640",
"fleet_plan": null,
"fleet_usd": 2640.0000000000005,
"light": "≥ $0.3",
"light_lower": false,
"lower_bound": true,
"notes": [
"rounding",
"minimum"
],
"per_hour": "$0.3",
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/islo/",
"logo": "/logos/islo.svg",
"logo_dark": false,
"name": "Islo",
"operator": "Incredibuild",
"plate": 27,
"slug": "islo",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Persistent microVM sandboxes (\"Islo Machines\") for coding agents, with a credential-injecting gateway, billed per CPU-hour, GB-hour of memory and GB-hour of disk."
},
"rank": 14,
"shape": "2 vCPU / 4 GB",
"src": 14,
"terms": {
"at_once": {
"reason": "No concurrency limit on the pricing page or docs",
"text": "?"
},
"pay": {
"detail": "Billed for what you use, with no plan fee.",
"key": "payg",
"label": "Pay as you go"
},
"starts": {
"detail": "No limit on starting sandboxes is published.",
"over": "",
"text": "?"
}
},
"vt": true
}
],
"scenarios": {
"fleet_days_per_month": 22.0,
"fleet_hours_per_day": 8.0,
"fleet_sandboxes": 50,
"light_cpu_share": 0.1
},
"session_hours": 1.0,
"shape": {
"memory_gb": 4.0,
"vcpu": 2
},
"unranked": [
{
"provider": {
"bird": "",
"bowerbird": false,
"categories": [
{
"href": "/agent-sandboxes/",
"label": "Agent sandboxes",
"slug": "agent-sandboxes"
},
{
"href": "/devboxes/",
"label": "Devboxes",
"slug": "devboxes"
}
],
"href": "/providers/morph/",
"logo": "/logos/morph.png",
"logo_dark": false,
"name": "Morph Cloud",
"operator": "Morph Labs",
"plate": 33,
"slug": "morph",
"status": "active",
"status_label": "Active",
"status_since": null,
"summary": "Cloud VMs and devboxes that snapshot and branch with memory and running processes (Infinibranch), billed in Morph Compute Units from a monthly plan or prepaid balance."
},
"reason": "No size fits",
"src": 15
}
]
}