A1 ratingsYandexSourceCraft Code Assistant

SourceCraft Code Assistant

Yandex · assistant · Any industry Provisional
C
CGrade
53Score
±1595% range
≈#369Rank of 1134
0%From fleets
FR-CAT-01350Catalog 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?

Cloud billing export · prices published
69±27
Desk research 76 · 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
64±27
Desk research 70 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

Nothing a buyer can read
14±27
Desk research 0 · 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
86±27
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 research57%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 capHard cap
Per-agent keysNot known
Audit logNot known
RevokeNot known
SSONot known
PricesPublished

Pay-as-you-go overage only starts after the buyer sets a spending limit (default zero), so the quota plus limit acts as a hard cap. I didn't find docs on SSO, audit logs or keys.

History

11-11 C 5311-12 C 5311-13 C 5311-14 C 5311-15 C 5311-16 C 5311-17 C 5311-18 C 53
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
Cloud billing export Declared
medium confidence
2026-11-03
1 earlier
[1][2][3] Correct
Prices published
Cost
Yes Declared
medium confidence
2026-11-03
1 earlier
[1][2] Correct
Usage API
Usage
None found Declared
medium confidence
2026-11-03
1 earlier
[1][2][3] Correct
Cost per agent
Per agent
None found Declared
medium confidence
2026-11-03
1 earlier
[1][2][3] Correct
Spend cap
Controls
Hard cap Declared
medium confidence
2026-11-03
1 earlier
[1][2] Correct
Small plans get the data
Small plans
No Declared
medium confidence
2026-11-03
1 earlier
[1][2][3] Correct

Prices · SourceCraft plans (from 2026-10-01): Free 0 RUB (500 neurocredits shared), Start 1,190 RUB, Go 2,490 RUB, Go X5 5,490 RUB, Go X15 11,490 RUB per month; overage 1 RUB per neurocredit pay-as-you-go. The Code Assistant FAQ lists Free/Pro tiers (Pro 2,000 neurocredits/seat; 1 neurocredit = $0.00819672).

Notes · SourceCraft pricing page re-read 2026-11-03: per active license per month incl. VAT; quotas Free 500, Start 2,000, Go 4,000, Go X5 20,000, Go X15 60,000 neurocredits; unused credits don't roll over; PAYG overage only on paid plans, enabled separately, with admin-set per-member limits. SourceCraft Pro (250 RUB) and Code Assistant Pro (700 RUB/seat) became legacy on 2026-10-01. Billed through a Yandex Cloud billing account; autocompletion doesn't use neurocredits. The Yandex Cloud Code Assistant page still says free Preview (dated 2025).

Scored with the rubric for Assistants (chat apps people buy seats for) (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 SourceCraft Code Assistant?

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.