Status
Is xKiro answeringright now?
We don't publish uptime history yet, so this page doesn't pretend to. Instead, your browser asks the API directly the moment you open it — the answer is about now, from where you are.
$ The check starts as soon as the page has loaded.
Public API
The endpoint your code calls
api.xkiro.com/v1/models
Through this website
The same API, reached via this site
xkiro.com/v1/models
The check starts as soon as the page has loaded.
From your server
Your agents don't run in a browser.
Run the same checks from the machine that calls us. They are the first two steps of our troubleshooting guide.
Troubleshooting guide- 01
Can you reach the API?
No key needed. Anything other than 200 here is the network, DNS or a proxy in front of you — not your key and not your request body.
$ curl -sS -o /dev/null -w "%{http_code}\n" https://api.xkiro.com/v1/models200 - 02
Is your key accepted?
401 means the key is missing, malformed or revoked. Check that the variable actually arrived — print its length, never its value.
$ curl -sS https://api.xkiro.com/v1/chat/completions \ -H "Authorization: Bearer $XKIRO_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-5.6-sol","messages":[{"role":"user","content":"hi"}]}'
Catalog
What's changing in the model list.
Read from the live catalog. When a model is retired, requests to its old ID return an error that names the replacement.
Browse all models- Scheduled retirements0
No retirements are scheduled.
Still failing?
Tell us. Include the model ID, the time with timezone and the full error body — that is usually enough to find the cause in one reply.
About uptime history: we don't publish it yet. When we do, it will be measured — not illustrated.