Runtime vs Superserve
Runtime costs $0.025 per vCPU-hour and Superserve costs $0.0504 per vCPU-hour. Runtime runs Firecracker microVMs and has no session limit. Superserve runs Firecracker microVMs and has no session limit.
Updated
Runtime
- Isolation
- Firecracker microVM
- Free tier
- 100 hours of a 1 GB machine in the first 30 days
- Max session
- No limit
Superserve
- Isolation
- Firecracker microVM
- Free tier
- $5 to start, plus $95 when you add billing
- Max session
- No limit
What is different
8 fields differ. The rest are the same or not listed.
Runtime
Superserve
- vCPU, per hour
- Runtime: $0.025
- Superserve: $0.0504
- RAM, per GiB-hour
- Runtime: $0.0075
- Superserve: $0.0162
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Superserve: Free
- Free tier
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Superserve: $5 to start, plus $95 when you add billing
- Billing
- Runtime: Active CPU time only
- Superserve: Per second
- Concurrent sandboxes
- Runtime: Up to 200
- Superserve: Up to 1,000
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Superserve: Python, TypeScript
- Integrations
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
- Superserve: Claude Agent SDK, LangChain, OpenAI Agents SDK, MCP, Claude Code
Full comparison
18 fields, at each provider's list price
Runtimewithruntime
Superservesuperserve
Pricing
- vCPU, per hour
- Runtime: $0.025
- Superserve: $0.0504
- RAM, per GiB-hour
- Runtime: $0.0075
- Superserve: $0.0162
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Superserve: Free
- Free tier
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Superserve: $5 to start, plus $95 when you add billing
- Paid plan from
- Runtime: Pay as you go
- Superserve: Pay as you go
- Billing
- Runtime: Active CPU time only
- Superserve: Per second
Limits
- Max session
- Runtime: No limit
- Superserve: No limit
- Idle stop
- Runtime: After 5 minutes
- Superserve: Not listed
- Largest sandbox
- Runtime: 16 vCPU · 64 GiB
- Superserve: 16 vCPU · 64 GiB
- Concurrent sandboxes
- Runtime: Up to 200
- Superserve: Up to 1,000
Platform
- Isolation
- Runtime: Firecracker microVM
- Superserve: Firecracker microVM
- GPU
- Runtime: No
- Superserve: Not listed
- Snapshots
- Runtime:
- Superserve:
- Pause and resume
- Runtime:
- Superserve:
Developer
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Superserve: Python, TypeScript
- Integrations
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
- Superserve: Claude Agent SDK, LangChain, OpenAI Agents SDK, MCP, Claude Code
Trust
- License
- Runtime: Not listed
- Superserve: Not listed
- BYOC
- Runtime: Not listed
- Superserve: In your AWS, GCP, or Azure account. Enterprise plan.
Hourly cost
One sandbox running for one hour
Runtime
Superserve
- 1 vCPU · 2 GiB
- Runtime: $0.040
- Superserve: $0.083
- 2 vCPU · 4 GiB
- Runtime: $0.080
- Superserve: $0.166
- 4 vCPU · 8 GiB
- Runtime: $0.160
- Superserve: $0.331
Compute only, at list rates.
Open the calculatorWhich one fits
Based on the fields above
Runtime fits when
- You use the Vercel AI SDK.
- You want the lower list price: $0.080 against $0.166 an hour for 2 vCPU and 4 GiB.
- Your code waits a lot: CPU is billed only while it is in use.
Superserve fits when
- You need the sandboxes in your own cloud account.
- You need SOC 2 Type II, HIPAA and GDPR.
More comparisons
Agent Sandbox vs Runtime- Agent Sandbox vs Superserve
Agent37 Cloud vs Runtime- Agent37 Cloud vs Superserve
AgentBay vs Runtime- AgentBay vs Superserve
- Alibaba Cloud Agent Sandbox vs Runtime
- Alibaba Cloud Agent Sandbox vs Superserve