Hacker News Reader

Comment by christinetyip | Hacker News Reader

It's been a bit disruptive to my workflows tbh. What alternatives are people using? Sell them to me please

You can try out a bunch of models on OpenRouter and see what works for you. Paying per token might be too expensive long term, but definitely a good way to figure out which models you like, and then look at providers.

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.

I've found my brain is a good alternative.

So are you offering api keys or...

Sorry, but I can't find "My Brain" anymore. Any alternatives?

I use both claude code and opencode w/ a fireworks.ai firepass subscription.

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.

I wanted to ask someone about the firepass subscription. It implies unlimited usage - sounds too good to be true. Is it? Can you leave your agent running all day?

I’m not entirely sure TBH. But I’ve been running huge loads against it and haven’t hit a limit yet. It’s far more stable and generous than Claude. And it’s fast, in a noticeable way. It’s $7/week and I’d rather run out of quota than get a surprise big bill. Still churning.

Yep, I have it running multiple OpenClaw instances all day. No issues.

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...

I was/am a fan of z.ai’s GLM models as a drop in replacement for Claude. But they more than doubled their prices recently. Still a ok alternative, but not really an amazing deal anymore.

I have been using turnstone with local models more. The open models are getting “good enough” that paying $100 or $200 a month is making less sense.

What sort of local models are we talking (and what sort of hardware)?

I pre-gen all my plans with Opus 4.6, and if there's an outage, I use pi with Kimi K2.5 via Fireworks. It's comparable to Sonnet.

Codex is okay. Not as refined but workable. I also had reasonable success with Qwen 3.6 Plus and opencode.

You could try writing code yourself. Most developers currently write code themselves.

It’s between your ears

Reply on news.ycombinator.com