Runtime vs tama
Runtime costs $0.025 per vCPU-hour and tama costs $0.01166 per vCPU-hour. Runtime runs Firecracker microVMs and has no session limit. tama runs full VMs and offers GPUs.
Updated
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
8 fields differ. The rest are the same or not listed.
Runtime
tama
- vCPU, per hour
- Runtime: $0.025
- tama: $0.01166
- RAM, per GiB-hour
- Runtime: $0.0075
- tama: $0.005523
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- tama: No charge for snapshots or stopped machines
- Billing
- Runtime: Active CPU time only
- tama: Per second
- Largest sandbox
- Runtime: 16 vCPU · 64 GiB
- tama: 32 vCPU · 128 GiB
- Isolation
- Runtime: Firecracker microVM
- tama: Full VM
- GPU
- Runtime: No
- tama:
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- tama: Python, TypeScript
Full comparison
18 fields, at each provider's list price
Runtimewithruntime
tamatama
Pricing
- vCPU, per hour
- Runtime: $0.025
- tama: $0.01166
- RAM, per GiB-hour
- Runtime: $0.0075
- tama: $0.005523
- Storage
- Runtime: $0.000119 per GiB-hour after 10 free GiB
- tama: No charge for snapshots or stopped machines
- Free tier
- Runtime: 100 hours of a 1 GB machine in the first 30 days
- tama: Not listed
- Paid plan from
- Runtime: Pay as you go
- tama: Pay as you go
- Billing
- Runtime: Active CPU time only
- tama: Per second
Limits
- Max session
- Runtime: No limit
- tama: Not listed
- Idle stop
- Runtime: After 5 minutes
- tama: Not listed
- Largest sandbox
- Runtime: 16 vCPU · 64 GiB
- tama: 32 vCPU · 128 GiB
- Concurrent sandboxes
- Runtime: Up to 200
- tama: Not listed
Platform
- Isolation
- Runtime: Firecracker microVM
- tama: Full VM
- GPU
- Runtime: No
- tama:
- Snapshots
- Runtime:
- tama:
- Pause and resume
- Runtime:
- tama:
Developer
- SDKs
- Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
- tama: Python, TypeScript
- Integrations
- Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code
- tama: Not listed
Trust
- License
- Runtime: Not listed
- tama: Not listed
- BYOC
- Runtime: Not listed
- tama: Not listed
Hourly cost
One sandbox running for one hour
Runtime
tama
- 1 vCPU · 2 GiB
- Runtime: $0.040
- tama: $0.023
- 2 vCPU · 4 GiB
- Runtime: $0.080
- tama: $0.045
- 4 vCPU · 8 GiB
- Runtime: $0.160
- tama: $0.091
Compute only, at list rates.
Open the calculatorWhich one fits
Based on the fields above
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.
- Your code waits a lot: CPU is billed only while it is in use.
tama fits when
- You need GPUs.
- You want each sandbox to be a full VM.
- You want the lower list price: $0.045 against $0.080 an hour for 2 vCPU and 4 GiB.
- You need a sandbox larger than 16 vCPU · 64 GiB.
More comparisons
Agent Sandbox vs Runtime- Agent Sandbox vs tama
Agent37 Cloud vs Runtime- Agent37 Cloud vs tama
AgentBay vs Runtime- AgentBay vs tama
- Alibaba Cloud Agent Sandbox vs Runtime
- Alibaba Cloud Agent Sandbox vs tama