Skip to main content
Independent MeasurementEndpoint record (L0 · L1)Published state: passLast probed: 2026-09-28 · 1 day ago

api.xfuel.app/v1/chat/completions

1.Catalog declaration

Catalog declaration for this endpoint
Resource URLhttps://api.xfuel.app/v1/chat/completions
Sourcecdp_bazaar
Declared methodPOST
Networkeip155:8453
Receiving address0x23f713411c30bbd9a989c9cbc22eb0b55f7f7334
Declared price (base units)2000
Catalog statusactive
First seen / last seen2026-08-25 01:58 UTC / 2026-09-29 01:02 UTC
Catalog-reported calls / payers (30d)61 / 11

2.Probe history

2026-09-082026-09-28
Figure 1. Probe timeline, last 30 probes for this endpoint (UTC). Filled = pass, crossed = fail, dashed = unverified. Same-day probes overlap. Marks closer than one mark width are stepped down one lane.
L0 probe history, newest first
Probed atMethodVerdictHTTPLatencyReason
2026-09-28 16:40 UTCPOSTpass402559 ms—
2026-09-27 22:40 UTCPOSTpass402782 ms—
2026-09-27 04:40 UTCPOSTpass402856 ms—
2026-09-26 13:40 UTCPOSTpass402962 ms—
2026-09-25 16:40 UTCPOSTpass402467 ms—
2026-09-24 22:40 UTCPOSTpass402715 ms—
2026-09-24 04:40 UTCPOSTpass402800 ms—
2026-09-23 13:40 UTCPOSTpass402698 ms—
2026-09-22 16:40 UTCPOSTpass402386 ms—
2026-09-21 22:40 UTCPOSTpass402771 ms—
2026-09-21 04:40 UTCPOSTpass402445 ms—
2026-09-20 13:40 UTCPOSTpass402519 ms—
2026-09-19 22:40 UTCPOSTpass402428 ms—
2026-09-19 04:40 UTCPOSTpass402439 ms—
2026-09-18 13:40 UTCPOSTpass402279 ms—
2026-09-17 16:40 UTCPOSTpass402419 ms—
2026-09-16 22:40 UTCPOSTpass402391 ms—
2026-09-16 13:40 UTCPOSTpass402656 ms—
2026-09-15 13:40 UTCPOSTpass402372 ms—
2026-09-14 22:40 UTCPOSTpass402504 ms—
2026-09-14 04:40 UTCPOSTpass402330 ms—
2026-09-13 16:40 UTCPOSTpass402439 ms—
2026-09-12 22:40 UTCPOSTpass402534 ms—
2026-09-12 13:40 UTCPOSTpass402322 ms—
2026-09-11 16:40 UTCPOSTpass402374 ms—
2026-09-11 04:40 UTCPOSTpass402281 ms—
2026-09-10 17:40 UTCPOSTpass402289 ms—
2026-09-09 23:40 UTCPOSTpass402320 ms—
2026-09-09 14:40 UTCPOSTpass402311 ms—
2026-09-08 23:40 UTCPOSTpass402386 ms—

3.L1 — real purchases

2 of 4 paid attempts settled with a receipt, and 2 of those also returned a 2xx response (delivered). Each settled row carries its on-chain transaction hash — the receipt is the evidence. A settled row reads as nonce-bound when the on-chain re-read also matched the one-time signature nonce we generated for that purchase, and amount + payee when it matched amount, payee, asset and chain with no nonce on record — the binding shipped on 2026-09-04, so earlier rows carry the weaker evidence and keep their label rather than being demoted (methodology). settled is the transfer we confirmed on-chain; delivered is the response arriving. A settled row whose paid request answered 5xx counts as settled and not as delivered — definitions.

A row marked tx from our index came back with no settlement receipt from the seller. Our own index of on-chain settlements found the transfer afterwards — our payer, this endpoint's payee, the exact amount, inside the time window — and the row goes through the same on-chain re-read as any other before it reads settled. The seller did not name that transaction; we did (methodology).

2 of those paid attempts are held as inconclusive rather than counted against this seller (0 settled and answered 4xx, 2 answered 4xx with no settlement receipt, 0 answered 402 or 5xx while our own payer wallet was out of USDC, 2026-09-13 00:00 to 2026-09-15 23:49 UTC). A 4xx says the request was not one the server would accept, and we cannot rule out that the request was ours to get wrong: vet402 buys with no API key of the seller's, and sends a POST body only when the seller declares one. This is the same principle the methodology already applied to path_template URLs, applied to the body and the authentication header as well. The rows are not deleted and not hidden — they are below, with their status and HTTP code, and they are out of the denominator for delivered (corrections).

2 of the paid attempts failed on vet402's side (for example our wallet was out of USDC, or we did not send the input the listing declares). The rows stay in the table; the embeddable badge below leaves them out of its count and names them as “vet402 side”.

Terms in this table

settled (nonce-bound)
vet402 confirmed the USDC transfer on-chain, and the on-chain re-read also matched the one-time nonce vet402 signed for that purchase.
settle_failed
vet402 signed a payment and got no settlement receipt back.
unsettled_4xx
held_reason in the export: the paid request got a 4xx with no settlement receipt and no transaction.
L2 no_declaration
the listing declares no output schema to check the response against.
L2 not_checked
not checked: the paid request did not answer 200, so there was no response to check against the listing's output schema.
Whose side
the same words as the seller page: seller's side only after failures on two different days (UTC), marked “under re-check”; vet402's side; or not sorted (the rules).
2/4
Figure 2. Settle-through: one cell per paid attempt. Filled = settled with an on-chain receipt, crossed = signed, and not settled on-chain.
L1 purchase history, newest first
Attempted atResultHTTPReceipt (tx)Latency
09-28 00:01settled (nonce-bound)2000xa9947f31…524d2287 ms
2000 units (≈ $0.002 USDC) · L2 no_declarationWhose side: no failure (delivered)
09-21 18:01settled (nonce-bound)tx from our index2000x102d4115…f1d52727 ms
2000 units (≈ $0.002 USDC) · L2 no_declarationWhose side: no failure (delivered)
09-15 12:08settle_failed400—475 ms
2000 units (≈ $0.002 USDC) · L2 not_checkedWhose side: vet402's side
09-09 01:01settle_failed400—480 ms
2000 units (≈ $0.002 USDC) · L2 not_checkedWhose side: vet402's side

Embed this record

Run this endpoint? Show the settle-through record vet402 measured — the badge reads 2/2 settled · 2 delivered · vet402 side 2 and updates as the record grows. It carries the host it is about and the date it was last measured, so a saved copy cannot pass itself off as current. It states a measurement, not a rating.

vet402: 2 of 2 paid attempts settled with an on-chain receipt, and 2 of those also returned a 2xx response. settled is the confirmed transfer; delivered is the response arriving. 2 further paid attempts failed on vet402's side (for example its wallet was out of USDC, or it did not send the input the listing declares) and are left out of these counts. A measurement of what happened when vet402 paid this endpoint, not a recommendation. (api.xfuel.app · measured 2026-09-28)

[![vet402 receipt](https://vet402.com/api/badge/endpoint/21881584-4d67-47cf-9d9c-6e5a94514b9c.svg)](https://vet402.com/observatory/e/21881584-4d67-47cf-9d9c-6e5a94514b9c)

Get one email when this record's verdict changes. No digest, no marketing — one message per change, and only for this endpoint. We first send one confirmation email; nothing else goes out until you confirm.

4.Catalog listing events

No listing changes observed.

unverified is not a failure; a fail is published only after two consecutive failing probes. Definitions: methodology.

5.Dispute this record

Think a measurement above is wrong? Say which probe or purchase and what you observed instead. One person reads it and replies. The record is never deleted on dispute: if it was wrong, the correction is published with the same weight; if it was right, it stands. Operators who control the receiving address can also sign a dispute via POST /api/v1/observatory/disputes (API reference), which re-measures through the normal publication gate.

About the purchase at 2026-09-02T19:00:56Z (UTC). The form starts with that time; add what you saw instead.

20–2,000 characters · 59 so far