A1 ratingsThinking Machines LabTinker

Tinker

Thinking Machines Lab · platform · Any industry Provisional
B
BGrade
68Score
±1595% range
≈#101Rank of 1136
0%From fleets
FR-CAT-01554Catalog 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?

Vendor cost API (tinker billing usage: hourly rows per usage type, base model, session, user and project with estimated gross USD (not invoice amounts), max 14-day window, lags a few hours; CSV/JSON export.) · 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?

tinker billing usage and tinker billing checkpoint-storage (CLI/SDK), org-wide with project/session breakdown.
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?

Audit log: By API
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
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 research52%Neutral starting point48%

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 keysNot known
Audit logBy API
RevokeNot known
SSONot known
PricesPublished

Audit log types (AuditLogEntry, events like checkpoint_read, project_grant_set) exist in the SDK API reference; retrieval endpoint not read. API keys created in console; scoping, revocation, spend caps and SSO not documented on pages read. Enterprise agreements via contact form.

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 2026-11-08. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-11-07.

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
high confidence
2026-11-07 [1][2] Correct
Prices published
Cost
Yes Declared
medium confidence
2026-11-07 [1][2][3] Correct
Usage API
Usage
tinker billing usage and tinker billing checkpoint-storage (CLI/SDK), org-wide with project/session breakdown. Declared
high confidence
2026-11-07 [1][2] Correct
Cost per agent
Per agent
partial Declared
high confidence
2026-11-07 [1][2] Correct
Audit log
Controls
By API Declared
medium confidence
2026-11-07 [1][2][3] Correct
Small plans get the data
Small plans
No Declared
high confidence
2026-11-07 [1][2] Correct

Prices · Per 1M tokens for prefill/sample/train, e.g. Inkling 2 Small $0.30 prefill, $1.00 sample, $1.50 train; checkpoint storage $0.10/GB-month; serverless inference beta/waitlist.

Notes · Costs shown before credits/commits. Attribution by project, session and user, not per agent key.

Scored with the rubric for Platforms and APIs (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 Tinker?

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.