Microsoft Foundry hosted agents vs SF Compute Autoresearch Sandboxes

Microsoft Foundry hosted agents costs $0.0994 per vCPU-hour. SF Compute Autoresearch Sandboxes bills memory only, at $0.04572 per GiB-hour. Microsoft Foundry hosted agents runs microVMs. SF Compute Autoresearch Sandboxes runs microVMs.

Updated Oct 23, 2026

Microsoft Foundry hosted agents

Runs your AI agent code on Azure, with each session in its own microVM.

Isolation: MicroVM
Free tier: Not listed
Max session: Not listed

Visit site Microsoft Foundry hosted agents profile

SF Compute Autoresearch Sandboxes

Isolated microVMs for AI agents that fork from a saved snapshot, part of SF Compute Autoresearch.

Isolation: MicroVM
Free tier: None
Max session: Not listed

Visit site SF Compute Autoresearch Sandboxes profile

What is different

6 fields differ. The rest are the same or not listed.

Field

Microsoft Foundry hosted agents

SF Compute Autoresearch Sandboxes

vCPU, per hour: Microsoft Foundry hosted agents: $0.0994; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Microsoft Foundry hosted agents: $0.0118; SF Compute Autoresearch Sandboxes: $0.04572
Billing: Microsoft Foundry hosted agents: Per second; SF Compute Autoresearch Sandboxes: Memory only
Largest sandbox: Microsoft Foundry hosted agents: 2 vCPU · 4 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Microsoft Foundry hosted agents: Up to 2,000; SF Compute Autoresearch Sandboxes: Up to 4,096
Integrations: Microsoft Foundry hosted agents: Claude Agent SDK, LangChain, MCP, OpenAI Agents SDK; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Full comparison

18 fields, at each provider's list price

Microsoft Foundry hosted agentsazure.microsoft.com/en-us/pricing/details/foundry-agent-serviceazure.microsoft.com

SF Compute Autoresearch Sandboxesautoresearch.sfcompute.com

Pricing

vCPU, per hour: Microsoft Foundry hosted agents: $0.0994; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Microsoft Foundry hosted agents: $0.0118; SF Compute Autoresearch Sandboxes: $0.04572
Storage: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage
Free tier: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: None
Paid plan from: Microsoft Foundry hosted agents: Pay as you go; SF Compute Autoresearch Sandboxes: Pay as you go
Billing: Microsoft Foundry hosted agents: Per second; SF Compute Autoresearch Sandboxes: Memory only

Limits

Max session: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Idle stop: Microsoft Foundry hosted agents: After 15 minutes; SF Compute Autoresearch Sandboxes: Not listed
Largest sandbox: Microsoft Foundry hosted agents: 2 vCPU · 4 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Microsoft Foundry hosted agents: Up to 2,000; SF Compute Autoresearch Sandboxes: Up to 4,096

Platform

Isolation: Microsoft Foundry hosted agents: MicroVM; SF Compute Autoresearch Sandboxes: MicroVM
GPU: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: Not listed
Snapshots: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes:
Pause and resume: Microsoft Foundry hosted agents:; SF Compute Autoresearch Sandboxes:

Developer

SDKs: Microsoft Foundry hosted agents: Python, JavaScript / TypeScript; SF Compute Autoresearch Sandboxes: Not listed
Integrations: Microsoft Foundry hosted agents: Claude Agent SDK, LangChain, MCP, OpenAI Agents SDK; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Trust

License: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: Not listed
BYOC: Microsoft Foundry hosted agents: Not listed; SF Compute Autoresearch Sandboxes: Not listed

Hourly cost

One sandbox running for one hour

Size

Microsoft Foundry hosted agents

SF Compute Autoresearch Sandboxes

1 vCPU · 2 GiB: Microsoft Foundry hosted agents: $0.123; SF Compute Autoresearch Sandboxes: $0.091
2 vCPU · 4 GiB: Microsoft Foundry hosted agents: $0.246; SF Compute Autoresearch Sandboxes: $0.183
4 vCPU · 8 GiB: Microsoft Foundry hosted agents: $0.492; SF Compute Autoresearch Sandboxes: $0.366

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Microsoft Foundry hosted agents fits when

You use the Claude Agent SDK, LangChain or the OpenAI Agents SDK.

SF Compute Autoresearch Sandboxes fits when

You use Claude Code.
You want the lower list price: $0.183 against $0.246 an hour for 2 vCPU and 4 GiB.
You need snapshots.
You want one rate for memory, with CPU included.

More comparisons

See all comparisons

Microsoft Foundry hosted agents

SF Compute Autoresearch Sandboxes

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Microsoft Foundry hosted agents fits when

SF Compute Autoresearch Sandboxes fits when

More comparisons

Related

Compare

Pricing

Browse