If you don't have regulatory hurdles to jump over then there are a whole raft of open-weight models that perform basically as well as Anthropic's offerings (and, in many cases, better because they're pulling fewer capacity-stretching shenanigans). Check out Kimi, DeepSeek, and GLM series models in particular with something like OpenCode or Pi as a coding harness. If you need a Claude-alike web UI then spin up Open WebUI in a container and expose it via cloudflared so you can use it on the go.
Kimi and DeepSeek are impressive for their size but still run slow on any hardware you or I would have. If you’re proposing we run those via a cloud service, I don’t see a reason to do that when it’s an inferior model and I still have to pay per token for it.
It's not just Claude API. See: "We are investigating reports of degraded performance affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork.". Seems pretty big to me.
It's software used by many here so of course you will hear about Claude downtime here.
I found out about this from my Claude Status menu bar I built last time it went down! It's invisible most of the time, unless the status goes down then a yellow or red marker appears. Improvements welcome: https://github.com/titojankowski/claude-status
We’re in the phase of society where we will just build something like this ourselves using an LLM and it will be built exactly how we want it and we don’t have to worry about malicious code or forking it and hoping the owner will merge our PR… it’s sad but that’s where we are for anything the size of a menu bar that pings a URL every minute.
I asked my OpenClaw agent to build me a Dyson sphere.
Yeap, all Oauth sessions got kicked and can't get back in. Welp, switching to Deepseek V4 Flash 0731 via OpenRouter.
Stoked that AI is in a place we have legitimate options available!
They are busy implementing text watermarks.
Time to write code by myself today)
Status page reports as down: https://status.claude.com/
Large volume of user generated reports
https://downdetector.com/status/claude-ai/
Dupe: https://news.ycombinator.com/item?id=49324068
My bad, I asked it to do something for me that really must have blown its mind
Seeing the same. Logging out of the desktop app and attempting to log back in just results in a reset of the authentication flow.
Use Claude through AWS Bedrock. Never been down for me.
Using it through Bedrock / API a 100$ subscription costs upwards of 6000$ a month.
How do you guys afford this, huge company that grants this?
Looks like their auth is broken. Do they ever publish postmortems?
still using anthropic in the big august 2026?
As opposed to what?
If you don't have regulatory hurdles to jump over then there are a whole raft of open-weight models that perform basically as well as Anthropic's offerings (and, in many cases, better because they're pulling fewer capacity-stretching shenanigans). Check out Kimi, DeepSeek, and GLM series models in particular with something like OpenCode or Pi as a coding harness. If you need a Claude-alike web UI then spin up Open WebUI in a container and expose it via cloudflared so you can use it on the go.
Kimi and DeepSeek are impressive for their size but still run slow on any hardware you or I would have. If you’re proposing we run those via a cloud service, I don’t see a reason to do that when it’s an inferior model and I still have to pay per token for it.
Dozens of providers of open-weight models. I have one session going with synthetic.new and another going with novita.ai right now.
But they’re slower (and benchmark worse) than Opus, GPT, et al. Why?
Claude is taking the rest of the day off, without alerting everyone. So it seems.
I'm sorry, but why is this on the front page with 2 up votes? Do we really need to be alerted every time the Claude API responds with an error?
Yea bc what are we supposed to do with ourselves now.
It's not just Claude API. See: "We are investigating reports of degraded performance affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork.". Seems pretty big to me.
It's software used by many here so of course you will hear about Claude downtime here.
bruh
I found out about this from my Claude Status menu bar I built last time it went down! It's invisible most of the time, unless the status goes down then a yellow or red marker appears. Improvements welcome: https://github.com/titojankowski/claude-status
We’re in the phase of society where we will just build something like this ourselves using an LLM and it will be built exactly how we want it and we don’t have to worry about malicious code or forking it and hoping the owner will merge our PR… it’s sad but that’s where we are for anything the size of a menu bar that pings a URL every minute.