Elevated errors on Claude.ai, API, Claude Code(claudestatus.com) |
Elevated errors on Claude.ai, API, Claude Code(claudestatus.com) |
Caveats: 1) May not be economic for those on flat-rate Anthropic subscription plans 2) I work at Google.
From developer experience, hosting them ourselves allows us to take advantage of our unique infra and deliver fastest time to first tokens of the providers.
However, it’s a very good “doer” - if I give it a list of well-scoped tasks, I can usually rely on it to execute them all correctly.
> Application error: a client-side exception has occurred while loading code.claude.com (see the browser console for more information).
Android app is still responding but no-go on claude.ai and I can't login with email
status.claude.com has an update:
Investigating - We are seeing increased errors on Claude.ai, API, and Claude Code Apr 15, 2026 - 14:53 UTC
- downdetector comment
The other big ones would be OpenAI with Codex and Google with their Gemini and their CLI or Antigravity. Or various IDE plugins or something like OpenCode on the tooling side. GitHub Copilot is pretty cheap and gives you basically unlimited autocomplete and generous monthly quotas that let you try out the most popular models. Also GLM 5.1 is pretty decent if you want to look at other subscriptions. Cerebras Code gave you a lot of tokens but their service wasn’t super stable last I tried and they also don’t give you the latest models.
Personally I just stick with Claude and the 100 USD Max subscription cause it still works really well, even the latest update today to the desktop app made it better (was slow and buggy a month ago, has been gradually getting better) and the Chrome plugin lets me get fully autonomous loops working.
Everything I set up in claude code I mirror in opencode.
I do more memory oriented things in CC and I end up doing a lot of things in opencode, especially when I want long-running things and I don't want to be limited by budget.
It also has GLM-5 hidden under a turbo router.
(Guide on how to enable it below): https://ai.sulat.com/fireworks-ai-the-ai-infrastructure-comp...
Claude Code returning: API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"},"request_id":"---"}
Over and over again!
I suspect they're highly oversubscribed, thus the reason why we're seeing them do other things to cut down on inference cost (ie changing their default thinking length).
A 500 error is almost never "just you".
( 404 is a client error, because it's the client requesting a file that does not exist, a problem with the client, not the server, who is _obviously_ blameless in the file not existing. )
8.30am on the US west coast
* Support really poor, raised a ticket last week and have heard nothing back at all * Separation of claude.ai accounts and console accounts is super confusing * Couldn't log into the platform since I had an old org in the process of deletion even though I was invited to a new one (had to wait 7 days!) * Payments for more API credits were broken for about a week * Claude chat has really gone to s*t unless it always was. Just getting back terrible answers to simple questions. * The desktop app is a web app pretending to be a desktop app that doesn't always know it is a desktop app so you get things like, "this will only work in the desktop app". Yes I know, this is the desktop app! "Oh sorry about that but you need to use the desktop app". * mcp integration and debugging is dreadful, just a combination of generic "an error ocurred" and sometimes nothing at all * MCP only supports OAuth for shared connectors but auth key doesn't work even with "local" servers that are not necessarily local, just the config is local.
You can put those on the health status!
This seems reasonable surge pricing approach to me: 1. Implement surge pricing for everyone for the peak 2 hours of the day if possible. 2 hours you can work around, 5 hours is too hard. 2. Give existing customers a one time credit for surge 3. Make sure the plans just consume credits at an accelerated rate (e.g. if on the max plan, i just get 1/2 usage during peak hours). 4. Exempt sonnet/haiku from surge (so people can keep using) 5. Make "auto" settings in claude code etc automatically adapt during surge hours, so people don't get surprises by default. 6. For the first 90 days, unofficially waive the fist $100 in surge for every user but notify them. To train users about the surge, and get them used to it without having them actually pay. 7. (I don't think they would do this but this would help) allow users to fall back to using something like GLM 5.1 or Gemma 4 automatically in outages, with a partnership to handle it. Its not ideal, but i would prefer it in "partner mode" than not. IMO they can charge like 10% on top of the partner fees for this if used in other times, but during outages or surge, partner mode is free. But 100% managed by Anthropic so users don't need to set things up and can just use the Anthropic harness.
Seriously take a look. Compare it to basically any other status page that companies make available. Their results are not flattering with all the downtime and issues. But it's far more transparent than most services I've experienced.
In fact, this proves that there is no AI Bubble and we are massively capacity constrained (aka we under-invested in infrastructure)
- Anthropic introduced stringent limits at peak hours. By "introduced" I mean announced it on a random dev's Xitter account
- Users suddenly started burning through all of their tokens even on trivial tasks. Anthropic never truly acknowledged it, their random devs posted "we're working on it".
- One of the workarounds was to somewhat quietly reduce default reasoning to medium
- OpenClaw and "usage through other tools" banned
- Announce "redesigned Claude Code Desktop App that lets you run many parallel sessions"
- Availability is still circling down the drain
- Dario Amodei is in continuous "trust us we have AGI coding is solved we don't need programmers just give us more money" mode now
> status.claude.com: "All Systems Operational"
It was a refactor that renamed some functions and consolidated some data structures.
Early twitter showed the fail whale as often as it showed tweets and yet it was an unstoppable juggernaut that people kept using.
In this case, Hanlon's razor has never been sharper.
Generally if you give people unused cycles to burn, they'll feel entitled to finding ways to burn them. So someone who is hitting the wall at x5 goes x20 and now has an extra +x10 to burn. Again, that's good if hardware is sitting around idle and you're encouraging innovation and exploration. It can make less sense when resources are scarce.
Maybe a good candidate for a Claude Routine! "By this time each day, brace for upcoming outage by preparing a comprehensive information package for Cursor to take over your work on active sessions" ...
I could search it myself, but haven't needed to. Getting it out of SQLite into some format Cursor understands should be trivial.
'Export the current conversation to a file or clipboard'
I've never hit the quota on Codex.
On Claude (Code), I used to hit it every other day before switching to Codex.
They're trying to push people to their new $100 tier, which has a boosted quota for now.
I know you added the defensive "almost" but if I had a dollar each time I saw a 500 due to the session cookies being sent by the client that made the backend explode - for whatever root cause - well, I would have a fatter wallet.
Bad input should be a 4xx, but if the server can't cope with it, that's still a 5xx.
Bonus points if due to the way that invalid requests are rejected, they are filtered out as invalid traffic and don't even show up as a spike in the application error logs.
This is how I learn that they have a "VPN" policy. Thinking of it maybe it makes sense, that is if it's what I think it is, but seems scummy nonetheless.
People should be ready, willing, and able to run an npm command every once in a while, particularly if their job may literally depend on it.
And no, I'm not apologizing for Anthropic's ineptitude. I'm offering an actual solution to this very simple problem.
I'm not an internet marketer but that sounds like a win win to me. People feel special, they get extra hype, and the service isn't broken.
In the case of Anthropic is fake availability.
Sam Altman explained the idea is to scale the thing up, and see what happens.
He hadn't claimed to offer a solution to the supply problem that would unfold.
Engineer roles dead in 6 months.
Disclosure: I have scars from a distributed system where errors propagated outwards and took down auth...
The dynamic thinking and response length is funny enough the best upgrade I've experienced with the service for more than a year. I really appreciate that when I say or ask something simple the answer now just comes back as a single sentence without having to manually toggle "concise" mode on and off again.
B. Everything is down, even auth.