Anthropic Code Execution vs Runtime
Anthropic Code Execution costs $0.05 per vCPU-hour and Runtime costs $0.025 per vCPU-hour. Anthropic Code Execution runs containers. Runtime runs Firecracker microVMs and has no session limit.
Updated
Anthropic Code Execution
- Isolation
- Container
- Free tier
- 1,550 free hours per month
- Max session
- Not listed
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
7 fields differ. The rest are the same or not listed.
Anthropic Code Execution
Runtime
- vCPU, per hour
- Anthropic Code Execution: $0.05
- Runtime: $0.025
- RAM, per GiB-hour
- Anthropic Code Execution: Included
- Runtime: $0.0075
- Free tier
- Anthropic Code Execution: 1,550 free hours per month
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Billing
- Anthropic Code Execution: Bundled machine time
- Runtime: Active CPU time only
- Largest sandbox
- Anthropic Code Execution: 1 vCPU · 5 GiB
- Runtime: 16 vCPU · 64 GiB
- Isolation
- Anthropic Code Execution: Container
- Runtime: Firecracker microVM
- SDKs
- Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
Full comparison
18 fields, at each provider's list price
Anthropic Code Executionplatform
Runtimewithruntime
Pricing
- vCPU, per hour
- Anthropic Code Execution: $0.05
- Runtime: $0.025
- RAM, per GiB-hour
- Anthropic Code Execution: Included
- Runtime: $0.0075
- Storage
- Anthropic Code Execution: Not listed
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- Free tier
- Anthropic Code Execution: 1,550 free hours per month
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- Paid plan from
- Anthropic Code Execution: Not listed
- Runtime: Pay as you go
- Billing
- Anthropic Code Execution: Bundled machine time
- Runtime: Active CPU time only
Limits
- Max session
- Anthropic Code Execution: Not listed
- Runtime: No limit
- Idle stop
- Anthropic Code Execution: Not listed
- Runtime: After 5 minutes
- Largest sandbox
- Anthropic Code Execution: 1 vCPU · 5 GiB
- Runtime: 16 vCPU · 64 GiB
- Concurrent sandboxes
- Anthropic Code Execution: Not listed
- Runtime: Up to 200
Platform
- Isolation
- Anthropic Code Execution: Container
- Runtime: Firecracker microVM
- GPU
- Anthropic Code Execution: Not listed
- Runtime: No
- Snapshots
- Anthropic Code Execution: Not listed
- Runtime:
- Pause and resume
- Anthropic Code Execution:
- Runtime:
Developer
- SDKs
- Anthropic Code Execution: Python, TypeScript, Go, Java, Ruby
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- Integrations
- Anthropic Code Execution: Not listed
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
Trust
- License
- Anthropic Code Execution: Not listed
- Runtime: Not listed
- BYOC
- Anthropic Code Execution: Not listed
- Runtime: Not listed
Hourly cost
One sandbox running for one hour
Anthropic Code Execution
Runtime
- 1 vCPU · 2 GiB
- Anthropic Code Execution: $0.050
- Runtime: $0.040
- 2 vCPU · 4 GiB
- Anthropic Code Execution: $0.100
- Runtime: $0.080
- 4 vCPU · 8 GiB
- Anthropic Code Execution: $0.200
- Runtime: $0.160
Compute only, at list rates.
Open the calculatorWhich one fits
Based on the fields above
Anthropic Code Execution fits when
- You need SOC 2 Type II and ISO 27001.
Runtime fits when
- You want each sandbox in its own microVM.
- You use the OpenAI Agents SDK, the Vercel AI SDK, the Claude Agent SDK, LangChain, MCP or Claude Code.
- You want the lower list price: $0.080 against $0.100 an hour for 2 vCPU and 4 GiB.
- You need snapshots.
More comparisons
Agent Sandbox vs Anthropic Code Execution- Agent Sandbox vs Runtime
Agent37 Cloud vs Anthropic Code Execution- Agent37 Cloud vs Runtime
AgentBay vs Anthropic Code Execution- AgentBay vs Runtime
- Alibaba Cloud Agent Sandbox vs Anthropic Code Execution
- Alibaba Cloud Agent Sandbox vs Runtime