Leaderboard / api.socialfetch.dev / endpoint
GET https://api.socialfetch.dev/v1/twitter/tweets
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 7 probes in the last 7 days.
- Category
- Web scrape by llm, confidence 70%
- Latest quote
- $0.014 on Base to 0x02C2…3043
- Uptime
- 100% / 7d, 100% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 5h ago
- Next probe
- 2026-11-18 00:01 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.014 | 0x02C2…3043 | default | yes | 10m ago |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 8h ago | Web scrape | 70% | llm | v1 | claude-haiku-5-5: Returns the content of a single tweet fetched by permalink or id, which is a page/profile content fetch rather than a search or enrichment. Social media content retrieval could also be read as web_search, but a single-item fetch by URL fits web_scrape best. |
| 25h ago | Web scrape | 60% | rules | v1 | rule web_scrape matched "fetch twitter social-data api socialfetch dev in:url" in metadata |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 5h ago | free | 402 | 101 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 11h ago | free | 402 | 88 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 17h ago | free | 402 | 110 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 24h ago | free | 402 | 119 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 30h ago | free | 402 | 90 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 36h ago | free | 402 | 139 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |
| 42h ago | free | 402 | 97 ms | v2 | yes | $0.014 | 0x02C2…3043 | — |