[arjie]

Certainly, yes. It's about $75/week. The harness picks the model appropriately but it's mostly Sonnet with some rare Opus and Haiku/Gemma. I was previously running on DeepSeek 3.2 but while per token costs are low, the actual amount of tokens required to produce results is high so total costs were actually higher!

I am also a Claude Code Max subscriber so the API use is in addition to the subscription, but it can't be helped. Claude Code is the best way for me to do work and the Claw is the best way for me to get an automated EA. I forgot something else: I also just text the bot to schedule meetings and it does that as well (I have a calendar delegated to its Google user).

I've got some space in a datacenter, and I was vacillating on getting a card and running some open models but when I actually exercised them, it turned out that the quality of open models was too far below the Claudes for my use-case. Still if you've got a 300W Blackwell-based RTX 6000 Pro and you want to trade for some 4090s, email me.

My claw powered by Claude is pretty trustworthy for my use-cases.

[senectus1]

do you really count this cost as value thats worth it?

I'm really surprised at the spending here...

[CalRobert]

I suppose it depends on how you value time. Paying a person to do it would cost more.

[robbomacrae]

“so the API use is in addition to the subscription, but it can't be helped.” - I beg to differ. OrcaBot.com is a claws that runs using vanilla Claude Code so you can do all that with your regular subscription. Disclosure: I’m the author. The only reason these other claws can’t offer that is because they front it with their own AI.

[arjie]

That's pretty cool. And when I first tried this, I tried to do it with a bash loop around `claude -p` and you can get quite far with that! But overall, I think I'd rather use their tools the way they've set them up to be used and pay them their $500/month total or whatever. I'm probably going to stick to this approach, but your thing is pretty neat so thank you for sharing.

[ffb7c5]

Just a heads up, I tried to use the continue with google button on your site, but running into "Bot verification failed". Using stock chrome browser, not running a VPN either

[robbomacrae]

Thanks for mentioning that. The bot filter has been causing trouble so I def need to go and look at it. Debated disabling it but any basic bot that starts a dashboard is spinning up a VM I pay for! Changing browser might be a workaround?

[arjie]

Seems like a Recaptcha failure. FWIW, I was able to sign in and everything. I didn't actually use the service though.

[Multiplayer]

I've read this and the replies and I don't understand - but want to. I have 6 agents spun up under one openclaw. 4 of them use my claude code max sub. 2 use my codex sub. I am not needing to use any metered API calls. Why are you?

[arjie]

I just don’t want to risk an account ban like I’ve heard others describe. But if it’s working for you that’s awesome! Saves a lot of money! I don’t mind the cost personally for the value.

Though you do have a point that OpenAI said their subscription is usable in third party apps so I should be using it then. Good point.

[Multiplayer]

Ah, the way I read your previous comment was that you were using both your plan and the api. I understand now.

[arjie]

Oh no, not at all. But your comment made me give the bot a ChatGPT subscription that it's using with the Codex endpoints since they've announced that they will be supporting 3rd party use of those endpoints. It's a bit slower than Sonnet through OpenRouter but it's vastly cheaper. Much appreciated for the advice!