io.github.Carlos-VLab/routing-services-courier
io.github.Carlos-VLab/routing-services-courier
Pay-per-call ($0.01 USDC) model-routing for AI coding agents: which LLM to call, cost vs. quality.
timeout probed 2026-10-15
fetch failed | Connect Timeout Error (attempted address: routing-courier-mcp-production.up.railway.app:443, timeout: 10000ms) | UND_ERR_CONNECT_TIMEOUT
- Endpoint
- https://routing-courier-mcp-production.up.railway.app/mcp (streamable-http)
- Host
- routing-courier-mcp-production.up.railway.app
- Registry
- active, updated 2026-09-17 · registry entry
- Reachable
- 6 of the last 6 probes
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-05 14:15 | alive | 369 ms | 1 | 245 | 127 |
| 2026-10-05 00:28 | alive | 223 ms | 1 | 127 | |
| 2026-10-04 10:01 | alive | 1.3 s | 1 | 127 | |
| 2026-10-04 07:55 | alive | 1.3 s | 1 | 127 | |
| 2026-10-03 20:35 | alive | 819 ms | 1 | 127 | |
| 2026-10-03 17:51 | alive | 530 ms | 1 | 127 |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Carlos-VLab/routing-services-courier)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.