Oriora Router is answering right now. Last checked 7 min ago.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
claude mcp add router --transport http https://api.orioralabs.com/mcp
https://api.orioralabs.com/mcp
[mcp_servers.router]
url = "https://api.orioralabs.com/mcp"
{
"mcpServers": {
"router": {
"url": "https://api.orioralabs.com/mcp"
}
}
}
{
"servers": {
"router": {
"type": "http",
"url": "https://api.orioralabs.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.orioralabs.com/mcp | streamable-http | sign-in | 227 ms | 7 min ago |
Test and compare prompts across any AI provider. Bring your own keys.
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
Find the right AI model for your job. Free discovery and ranking; tests on your own key.
Read, start and move the routines on your iPhone; suggest changes you approve on the phone.
Deploy and run your projects on Pethost, your own hosting.
Run AI agent evaluations on your own model keys, and publish runs others can review and re-run.
Find the cheapest AI model that passes your tests: audit repo models, build evals, routing, sizing
x402 router-proxy + 79 keyless pay-per-call tools on Base. Pay once, we run the best tool.
Answers built from our own checks of this server.