boat vs Runtime
boat costs $0.009 per vCPU-hour and Runtime costs $0.025 per vCPU-hour. boat runs full VMs and has no session limit. Runtime runs Firecracker microVMs and has no session limit.
Updated
boat
- Isolation
- Full VM
- Free tier
- 7-day free trial with 25 hours of compute
- Max session
- No limit
Runtime
- Isolation
- Firecracker microVM
- Free tier
- 100 hours of a 1 GB machine in the first 30 days
- Max session
- No limit
What is different
12 fields differ. The rest are the same or not listed.
boat
Runtime
- vCPU, per hour
- boat: $0.009
- Runtime: $0.025
- RAM, per GiB-hour
- boat: Included
- Runtime: $0.0075
- Storage
- boat: Free
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Free tier
- boat: 7-day free trial with 25 hours of compute
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Paid plan from
- boat: $20 / month
- Runtime: Pay as you go
- Billing
- boat: Bundled machine time
- Runtime: Active CPU time only
- Largest sandbox
- boat: 16 vCPU · 32 GiB
- Runtime: 16 vCPU · 64 GiB
- Concurrent sandboxes
- boat: Up to 2,000
- Runtime: Up to 200
- Isolation
- boat: Full VM
- Runtime: Firecracker microVM
- Pause and resume
- boat: No
- Runtime:
- SDKs
- boat: Python, JavaScript / TypeScript
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Integrations
- boat: MCP, Claude Code
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
Full comparison
18 fields, at each provider's list price
boatdocs
Runtimewithruntime
Pricing
- vCPU, per hour
- boat: $0.009
- Runtime: $0.025
- RAM, per GiB-hour
- boat: Included
- Runtime: $0.0075
- Storage
- boat: Free
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Free tier
- boat: 7-day free trial with 25 hours of compute
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Paid plan from
- boat: $20 / month
- Runtime: Pay as you go
- Billing
- boat: Bundled machine time
- Runtime: Active CPU time only
Limits
- Max session
- boat: No limit
- Runtime: No limit
- Idle stop
- boat: Not listed
- Runtime: After 5 minutes
- Largest sandbox
- boat: 16 vCPU · 32 GiB
- Runtime: 16 vCPU · 64 GiB
- Concurrent sandboxes
- boat: Up to 2,000
- Runtime: Up to 200
Platform
- Isolation
- boat: Full VM
- Runtime: Firecracker microVM
- GPU
- boat: No
- Runtime: No
- Snapshots
- boat:
- Runtime:
- Pause and resume
- boat: No
- Runtime:
Developer
- SDKs
- boat: Python, JavaScript / TypeScript
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Integrations
- boat: MCP, Claude Code
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
Trust
- License
- boat: Not listed
- Runtime: Not listed
- BYOC
- boat: Not listed
- Runtime: Not listed
Hourly cost
One sandbox running for one hour
boat
Runtime
- 1 vCPU · 2 GiB
- boat: $0.009
- Runtime: $0.040
- 2 vCPU · 4 GiB
- boat: $0.018
- Runtime: $0.080
- 4 vCPU · 8 GiB
- boat: $0.036
- Runtime: $0.160
Compute only, at list rates.
Open the calculatorWhich one fits
Based on the fields above
boat fits when
- You want each sandbox to be a full VM.
- You want the lower list price: $0.018 against $0.080 an hour for 2 vCPU and 4 GiB.
Runtime fits when
- You want to pay only for usage, with no plan fee.
- You want each sandbox in its own microVM.
- You use the OpenAI Agents SDK, the Vercel AI SDK, the Claude Agent SDK or LangChain.
- You need pause and resume.
More comparisons
Agent Sandbox vs boat- Agent Sandbox vs Runtime
Agent37 Cloud vs boat- Agent37 Cloud vs Runtime
AgentBay vs boat- AgentBay vs Runtime
- Alibaba Cloud Agent Sandbox vs boat
- Alibaba Cloud Agent Sandbox vs Runtime