A1 ratingsMistral AIMistral Agents API

Mistral Agents API

Mistral AI · framework · Any industry
B
BGrade
65Score
±1095% range
#154Rank of 1136
0%From fleets
FR-CAT-00115Catalog no.

The six pillars

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

Can you see what it costs?

Vendor cost API (Mistral Admin API GET /v1/admin/usage (cost and consumption incl. connectors, libraries)) · prices published
75±38
Desk research 100 · 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?

Mistral Admin API GET /v1/admin/usage (by workspace and month)
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 workspace
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 · Cost endpoint filterable by workspace; not per API key. le Chat analytics also offer a by_agent_stats activity breakdown.
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: Hard cap · Per-agent keys: Scoped · Audit log: Console only · Revoke: Console only · SSO: SSO + SCIM
69±38
Desk research 88 · 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 research73%Neutral starting point28%

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 capHard cap
Per-agent keysScoped
Audit logConsole only
RevokeConsole only
SSOSSO + SCIM
PricesPublished

The Admin API sets an organization-wide monthly spend limit, and per-workspace caps exist, with API keys scoped to a workspace. Audit logs are Enterprise-only and shown in the Admin Panel, with no export. SAML SSO is an Enterprise feature and basic SCIM is offered.

History

11-12 B 6511-13 B 6511-14 B 6511-15 B 6511-16 B 6511-17 B 6511-18 B 6511-19 B 65
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
Vendor cost API Declared
high confidence
2026-11-09
2 earlier
[1][2][3] Correct
Prices published
Cost
Yes Inferred 2026-11-09
2 earlier
[1][2][3][4] Correct
Usage API
Usage
Mistral Admin API GET /v1/admin/usage (by workspace and month) Declared
high confidence
2026-11-09
2 earlier
[1][2][3] Correct
Cost per agent
Per agent
By workspace Declared
high confidence
2026-11-09
2 earlier
[1][2][3] Correct
How an agent reports out
Reports out
Admin API Declared
high confidence
2026-11-09
2 earlier
[1][2][3] Correct
Per-agent keys
Controls
Scoped Inferred 2026-11-09
2 earlier
[1][2][3][4] Correct
Audit log
Controls
Console only Verified 2026-11-16
3 earlier
[1][2][3][4] Correct
Revoke access
Controls
Console only Inferred 2026-11-09
2 earlier
[1][2][3][4] Correct
Spend cap
Controls
Hard cap Inferred 2026-11-09
2 earlier
[1][2][3][4] Correct
SSO
Controls
SSO + SCIM Inferred 2026-11-09
2 earlier
[1][2][3][4] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-11-09
2 earlier
[1][2][3] Correct

Prices · Per-token model pricing (e.g. Mistral Large $0.5/$1.5 per 1M in/out); batch 50% off; connectors/tools billed separately

Notes · The Enterprise-only Admin API (GET /v1/admin/usage) returns cost by category and can filter by workspace, but not by API key or model, so splitting cost per agent needs separate workspaces. GET/POST /v1/admin/spend-limit reads and sets an organization-wide monthly limit (checked 2026-11-09).

Scored with the rubric for Open-source frameworks (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

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

RefFactChangeDecision
-Cost per agentby_workspace → exactrejected 2026-10-26

Run agents on Mistral Agents API?

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.