Free tool / live
Is the AI API down?
Live status of OpenAI, Anthropic, Gemini and more, read straight from each provider's own status page.
Live / refreshes every minute
One page for every provider.
Right now
Checking…
Last checked
—
Refreshes every minute while this tab is open
Read from each provider’s own status page
Status is only as fast as the provider's own page, and providers often post an incident minutes after users first see errors. If a provider's feed cannot be read, it is shown as “Unknown”, never as operational. For problems in your own traffic, you need your own monitoring.
How it works
Three steps, no sign-up.
- 01
Open the page
Status is read from each provider's public status feed when you load it.
- 02
Look for problems
Each provider shows its state, open incidents and any affected components.
- 03
Open the official page
Every card links to the provider's own status page for the full story.
Questions people ask
Where does this data come from?
Directly from each provider's public status feed, fetched by our server and cached for about a minute. We do not guess or run our own checks.
Why does a provider show as Unknown?
Its status feed could not be reached or was not in a format we understand. We never show green without a real answer. Use the link to check its page.
Why is the API failing for me when the page says operational?
Status pages lag, and problems can be limited to one model, region or account. Check your own error rates and latency, which is what Tracify shows.
How often does it update?
The page checks once a minute while it is open, and the server caches answers for about a minute.
Can I get alerts when a provider goes down?
Tracify alerts you when error rates or latency jump in your own agent traffic, which usually shows up before a status page does.
More free tools
- Agent log checker
Paste a log or trace. See where it failed, what was slow and what wasted tokens.
- Token counter
Paste text. See the token count and price on GPT, Claude, Gemini and Llama.
- Model price comparison
Every model's price in one table, plus what your app costs per month on each.
- Prompt cost checker
Paste a prompt. Get a shorter, cheaper version and what it costs on each model.
Now measure the real thing.
Send a first trace and see the true cost, speed and failures of every run.