Skip to content

Cloudflare D1

DatabaseREST · cloudflare-d1-rest-v4

Serverless SQLite databases on Cloudflare's network.

Overall score

46.2/100

cloudflare-d1-rest-v4

Measured Oct 5, 2026

Status

Ranked

Complete benchmark. `overall` is a weighted average of the applicable criteria, comparable to other surfaces in the same category and the same rubric version.

Coverage

78% of the rubric

Surfaces
evaluated.

We score a surface, not a product. One product often exposes several, and they are not worth the same.

cloudflare-d1-rest-v4restprimary

78% coverage

46.2/100

Criterion
by criterion.

Measured on cloudflare-d1-rest-v4, rubric v0.2.0. A criterion with no score is not counted as zero: it is excluded and the weights are renormalised.

Offload Valuejudged · weight 15 · Oct 5, 2026

30/100

The documented endpoint is a generic SQL query interface to a serverless database (D1) within Cloudflare's API surface. It stores and retrieves data the agent supplies; the agent must author the SQL and carry all reasoning. SQL execution is modest computation offload (joins/aggregations over stored rows persist state the agent cannot hold), but there is no proprietary data, no compliance logic, no real-world side effect, and no inference-replacing capability. Essentially CRUD with persistence.

Interaction Costmeasured · weight 15 · Oct 5, 2026

18/100

Median over 2 successful run(s): 39433 tokens, 3.5 calls. Ratio to the best in "backend-database" (4 surfaces measured, v0.2 scale). Cold, without documentation: 1/1 succeeded.

Error Recoverabilityprobed · weight 15 · Oct 5, 2026

40/100

unknown_endpoint → HTTP 404, clarity 30/100 (field named: no, allowed values: no, RFC 9457: no) · wrong_type → HTTP 400, clarity 75/100 (field named: yes, allowed values: yes, RFC 9457: no) · hallucinated_enum → HTTP 400, clarity 55/100 (field named: yes, allowed values: no, RFC 9457: no) · unknown_field → HTTP 200, clarity 0/100 (field named: no, allowed values: no, RFC 9457: no)

Doc Legibilitymeasured · weight 12 · Oct 5, 2026

41/100

text/markup ratio 5.4% (weight 30) · renders without JavaScript: yes (weight 25) · machine-readable spec: none found (weight 25) · llms.txt: https://developers.cloudflare.com/llms.txt (weight 10) · 1 runnable example(s) (weight 10). Weighted average over 100 points of available sub-criteria.

Auth Frictionmeasured · weight 10 · Oct 5, 2026

95/100

Authorization: Bearer <key>, verified by a successful call. One header, no ceremony.

Safety & Reversibilityprobed · weight 10

—/100

If I retry after a timeout, do I charge the customer twice?

Payload Efficiencyprobed · weight 8

—/100

Can I ask for only the fields I need, or do I have to swallow 200 attributes to extract one?

Task Atomicitymeasured · weight 6 · Oct 5, 2026

57/100

Median over 2 successful run(s): 39433 tokens, 3.5 calls. Ratio to the best in "backend-database" (4 surfaces measured, v0.2 scale). Cold, without documentation: 1/1 succeeded.

Prior Knowledge Coveragemeasured · weight 5 · Oct 5, 2026

100/100

Median over 2 successful run(s): 39433 tokens, 3.5 calls. Ratio to the best in "backend-database" (4 surfaces measured, v0.2 scale). Cold, without documentation: 1/1 succeeded.

Async Compatibilityprobed · weight 2

—/100

If the operation is asynchronous, can I get the result without hosting a web server?

Tool-Native (MCP)binary · weight 2

—/100

Does the vendor publish an official, maintained MCP server?

Runs, verified
never on the agent’s word.

Every row is a real attempt at the category’s canonical task. Success is verified by reading the created resource back.

TaskTokensCallsErrorsDocsResult
store-and-query-record8,57030withoutverified
store-and-query-record69,83941withverified
store-and-query-record9,02730withverified