A1 ratingsOpenAIOpenAI Agents SDK

OpenAI Agents SDK

OpenAI · framework · Any industry
A
AGrade
74Score
±1095% range
#29Rank of 1134
0%From fleets
FR-CAT-00904Catalog no.

The six pillars

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

Can you see what it costs?

Vendor cost API (OpenAI Costs API) · prices published
86±27
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?

Agents traces export GET /v1/agents/sessions/{session_id}/traces (OTLP JSON); OpenAI Usage API
86±27
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
86±27
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?

SDK
66±17
Desk research 70 · 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: By API · Revoke: By API · SSO: SSO + SCIM
90±17
Desk research 100 · 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
14±27
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 research74%Neutral starting point26%

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 logBy API
RevokeBy API
SSOSSO + SCIM
PricesPublished

Price changes: Services Agreement: pricing-page changes take effect 14 days after posting; material agreement changes get at least 30 days' notice.

API platform: org/project monthly spend limits enforce a hard stop (429 organization_/project_spend_limit_exceeded) only when 'Enforce a hard limit' is on; enforcement is not instantaneous so spend can slightly exceed the limit; spend alerts alone do not cap. Project service accounts and Restricted/Read-only keys with per-endpoint scopes; per-project model allow-lists and rate limits. Admin API lists/deletes project API keys; Audit Logs API (must be enabled, key needs Audit Logs read scope). SCIM for API orgs on Custom/Unlimited billing plans (configurable independently of SSO).

History

11-12 A 7411-13 A 7411-14 A 7411-15 A 7411-16 A 7411-17 A 7411-18 A 7411-19 A 74
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
medium confidence
2026-10-25
1 earlier
[1][2][3] Correct
Prices published
Cost
Yes Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Usage API
Usage
Agents traces export GET /v1/agents/sessions/{session_id}/traces (OTLP JSON); OpenAI Usage API Declared
medium confidence
2026-10-25
1 earlier
[1][2][3] Correct
Cost per agent
Per agent
Exact, per key or project Declared
medium confidence
2026-10-25
1 earlier
[1][2][3] Correct
How an agent reports out
Reports out
SDK Declared
high confidence
2026-10-25
1 earlier
[1] Correct
Per-agent keys
Controls
Scoped Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Audit log
Controls
By API Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Revoke access
Controls
By API Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Spend cap
Controls
Hard cap Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
SSO
Controls
SSO + SCIM Declared
high confidence
2026-10-25
1 earlier
[1][2][3][4] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-10-25
1 earlier
[1][2][3] Correct

Prices · SDK is free; you pay OpenAI API token/tool prices (e.g. GPT-6-Luna $0.10 in / $0.50 out per 1M tokens).

Notes · Trace token counts are explicitly not a final bill and can change as usage arrives; per-agent span usage excludes subagents. Traces export needs org enablement, api.traces.read or api.agents.read, and header OpenAI-Beta: agents=v1. Use one API key or project per agent so the Costs API (1d buckets, Admin key) can attribute dollars.

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

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

Run agents on OpenAI Agents SDK?

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.