A1 ratingsMicrosoftMicrosoft Foundry

Microsoft Foundry

Microsoft · platform · Any industry
B
BGrade
64Score
±895% range
#179Rank of 1136
0%From fleets
FR-CAT-01203Catalog no.

The six pillars

Each bar is the score; the bracket is its 95% range.

Can you see what it costs?

Cloud billing export (Azure Cost Management Query API)
66±17
Desk research 70 · counts for 25% · A cost API you can call scores highest; an admin console or cloud billing export next; a card statement or emailed invoice is all some products leave you. Published prices add to it.

Can you see how much it's used?

Azure Cost Management Query API (meter-level usage by resource/resource group)
90±17
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

By project
66±17
Desk research 70 · counts for 15% · Exact (one key or project per agent) beats by-project, by-workspace or by-user.

Can an agent on it report out?

Admin API · Query Cost Management by subscription/resource group/tags; agents on Foundry can call it with Azure credentials.
58±17
Desk research 60 · counts for 15% · A remote MCP connector scores highest, then a local MCP server, an SDK, an API or a workflow step; copy-and-paste lowest. Any open standard counts, not just FleetRegistry.

Can you control spend and access?

Spend cap: Alerts only · Per-agent keys: Scoped · Audit log: Console only · Revoke: By API
70±27
Desk research 78 · counts for 20% · Hard spend caps (30%), scoped per-agent keys (25%), an audit log you can read by API (20%), revoking by API (15%), SSO with SCIM (10%).

Does it work on small plans?

Small plans don't get the data
10±17
Desk research 0 · counts for 10% · Whether the plan a person or small business buys gets the cost and usage data at all.

Where the evidence comes from

Independent fleets0%Desk research78%Neutral starting point22%

Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.

Controls on record

Spend capAlerts only
Per-agent keysScoped
Audit logConsole only
RevokeBy API
SSONot known
PricesNot known

New name for Azure AI Foundry with the same controls: alert-only budgets, Entra RBAC (keys bypass RBAC), Purview audit coverage.

History

11-12 B 6411-13 B 6411-14 B 6411-15 B 6411-16 B 6411-17 B 6411-18 B 6411-19 B 64
Rated since 2026-10-02. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.

Every fact, with its rung and source

Each fact stands on its own source and its own rung of the evidence ladder (Rule N2.1). Verified Observed Declared Inferred. The weakest fact in a pillar sets its weight.

FactValueRungCheckedSources
How a buyer sees cost
Cost
Cloud billing export Declared
high confidence
2026-10-24
1 earlier
[1] Correct
Usage API
Usage
Azure Cost Management Query API (meter-level usage by resource/resource group) Declared
high confidence
2026-10-24
1 earlier
[1] Correct
Cost per agent
Per agent
By project Declared
high confidence
2026-10-24
1 earlier
[1] Correct
How an agent reports out
Reports out
Admin API Declared
high confidence
2026-10-24
1 earlier
[1] Correct
Per-agent keys
Controls
Scoped Declared
medium confidence
2026-10-24
1 earlier
[1][2][3] Correct
Audit log
Controls
Console only Declared
medium confidence
2026-10-24
1 earlier
[1][2][3] Correct
Revoke access
Controls
By API Declared
medium confidence
2026-10-24
1 earlier
[1][2][3] Correct
Spend cap
Controls
Alerts only Declared
medium confidence
2026-10-24
1 earlier
[1][2][3] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-10-24
1 earlier
[1] Correct

Prices · Pay-as-you-go, no upfront cost; models billed per token, tools and search priced separately

Notes · Re-checked 2026-10-24: consumption pricing by the models and tools used; hosted agents have zero idle cost; no rates on the product page.

Scored with the rubric for Platforms and APIs (Rule N7.1). Each pillar blends a neutral 50, desk facts weighted by rung, and independent fleets. A1 is 85+ with fleet proof, A 70, B 55, C 40, D 25, E below. Part N of the Rules

Corrections

1 awaiting review. Accepted corrections are published in the corrections register with an FR-C number.

Run agents on Microsoft Foundry?

Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.