
Dify
LangGenius · platform · Any industry Provisional
BGrade
61Score
±1595% range
≈#234Rank of 1136
0%From fleets
FR-CAT-00942Catalog no.
Provisional: the range is wide because some facts are thin or not yet known. It narrows as research and fleets fill in.
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
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?
No usage API found
Desk research 50 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.
Can you tie cost to one agent?
By project
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?
Remote MCP connector
Desk research 100 · 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?
Per-agent keys: Scoped · Audit log: Console only · SSO: SSO + SCIM
Desk research 85 · 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
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 research58%Neutral starting point43%
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 capNot known
Per-agent keysScoped
Audit logConsole only
RevokeNot known
SSOSSO + SCIM
PricesPublished
Re-checked 2026-10-21. Dify API keys are scoped per app or per knowledge base. SSO (SAML, OIDC, OAuth2), SCIM 2.0 sync, RBAC (Owner/Admin/Editor/Normal) and member operation logs are Enterprise-only (custom priced), with no audit export/API found; Cloud plans cap message credits rather than spend (after credits run out you switch to your own model key), and the self-hosted community edition lacks these enterprise controls.
History
11-12 B 6111-13 B 6111-14 B 6111-15 B 6111-16 B 6111-17 B 6111-18 B 6111-19 B 61
Rated since 2026-10-02. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.Run agents on Dify?
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.