A1 ratingsUpstageDocument Classify

Document Classify

Upstage · tool · Any industry
B
BGrade
55Score
±1495% range
≈#338Rank of 1134
0%From fleets
FR-CAT-01326Catalog no.

The six pillars

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

Can you see what it costs?

Only your card statement (false) · prices published
42±17
Desk research 40 · 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?

false
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?

partial
50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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?

50±59
Not known yet. Sits at a neutral 50 with a wide range until facts arrive · 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: Not scoped · Revoke: Console only
73±17
Desk research 79 · 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 research56%Neutral starting point44%

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 keysNot scoped
Audit logNot known
RevokeConsole only
SSONot known
PricesPublished

Owner sets a monthly (UTC) budget limit in Dashboard > Billing; requests blocked once reached (up to ~1s enforcement lag). API keys belong to an Organization (Owner/Member roles); per-key usage/cost visible; removed member's keys revoked immediately, revoked keys cannot be reactivated. No SSO or audit log documented for the Console.

History

11-11 B 5511-12 B 5511-13 B 5511-14 B 5511-15 B 5511-16 B 5511-17 B 5511-18 B 55
Rated since 2026-10-05. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-04.

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 your card statement Declared
high confidence
2026-11-03
1 earlier
[1] Correct
Prices published
Cost
Yes Declared
high confidence
2026-11-03
1 earlier
[1][2] Correct
Usage API
Usage
No Declared
high confidence
2026-11-03
1 earlier
[1] Correct
Cost per agent
Per agent
partial Declared
high confidence
2026-11-03
1 earlier
[1] Correct
Per-agent keys
Controls
Not scoped Declared
high confidence
2026-11-03
1 earlier
[1][2] Correct
Revoke access
Controls
Console only Declared
high confidence
2026-11-03
1 earlier
[1][2] Correct
Spend cap
Controls
Hard cap Declared
high confidence
2026-11-03
1 earlier
[1][2] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-11-03
1 earlier
[1] Correct

Prices · $0.004/page on the Console price list (node processing free during Beta inside Studio).

Notes · Pricing page re-read 2026-11-03. Console API is pay-as-you-go or prepaid credits (monthly/yearly commitment tiers with 10-40% bonus credits that expire with the commitment, auto-recharge); credit card only; usage continues on the card when credits run out. Console shows per-key usage and cost; no usage/cost API found. Classify inside Studio is free during Beta.

Scored with the rubric for Agents and agent platforms (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

Run agents on Document Classify?

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.