A1 ratingsPydanticPydantic AI

Pydantic AI

Pydantic · framework · Any industry
B
BGrade
68Score
±1095% range
#101Rank of 1134
0%From fleets
FR-CAT-00918Catalog no.

The six pillars

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

Can you see what it costs?

Only through a gateway you run · prices published
55±38
Desk research 60 · 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?

OpenTelemetry metrics gen_ai.client.token.usage and operation.cost (to Logfire or any OTel backend)
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?

Exact, per key or project
90±17
Desk research 100 · 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?

Local MCP server · Framework has MCP client/server support and emits per-run token and estimated cost via OTel; an agent can report out directly.
74±17
Desk research 80 · 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: One shared key · Audit log: None · Revoke: None · SSO: None
40±38
Desk research 30 · 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 keysOne shared key
Audit logNone
RevokeNone
SSONone
PricesPublished

Open-source framework. UsageLimits caps requests, tool calls, tokens and cost_limit (USD) per run and raises UsageLimitExceeded; checks run after each response, so the crossing request is still billed. A newer SpendLimits harness caps USD per run/day/month/scope as a soft brake. Keys, audit and SSO only via the hosted Gateway/Logfire.

History

11-12 B 6811-13 B 6811-14 B 6811-15 B 6811-16 B 6811-17 B 6811-18 B 6811-19 B 68
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
Only through a gateway you run Declared
high confidence
2026-10-27
1 earlier
[1][2] Correct
Prices published
Cost
Yes Inferred 2026-10-27
2 earlier
[1][2][3] Correct
Usage API
Usage
OpenTelemetry metrics gen_ai.client.token.usage and operation.cost (to Logfire or any OTel backend) Declared
high confidence
2026-10-27
1 earlier
[1][2] Correct
Cost per agent
Per agent
Exact, per key or project Declared
high confidence
2026-10-27
1 earlier
[1][2] Correct
How an agent reports out
Reports out
Local MCP server Declared
high confidence
2026-10-27
1 earlier
[1][2] Correct
Per-agent keys
Controls
One shared key Inferred 2026-10-27
2 earlier
[1][2][3] Correct
Audit log
Controls
None Inferred 2026-10-27
2 earlier
[1][2][3] Correct
Revoke access
Controls
None Inferred 2026-10-27
2 earlier
[1][2][3] Correct
Spend cap
Controls
Hard cap Inferred 2026-10-27
2 earlier
[1][2][3] Correct
SSO
Controls
None Inferred 2026-10-27
2 earlier
[1][2][3] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-10-27
1 earlier
[1][2] Correct

Prices · Free (MIT); optional Logfire observability is paid

Notes · Open-source (MIT) framework that emits per-request token and estimated USD cost as OTel metrics (gen_ai.client.token.usage, operation.cost). Logfire has a perpetual free tier plus paid tiers. Actual billing stays with the model provider.

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

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

Run agents on Pydantic AI?

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.