Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

braw.dev

Post reply on HN
Print view View original

111–120 of 265 posts

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#111

Post by napoleond »

BeetleB wrote: post #101
therealpygon wrote: post #78

Earlier quoted context omitted.

I agree with you in certain circumstances, but not really for internal user inference. OpenRouter is great if you need to maintain uptime, but for basic usage (chat/coding/self-agents) you can do all of what you mentioned and more with a LiteLLM instance. The number of companies that send a bill is rarely a concern when it comes to “is work getting done”, but I agree with you that minimizing user friction is best. Fo…

The two things I like about OpenRouter: 1. The LLM provider doesn't know it's you (unless you have personally identifiable information in your queries). If N people are accessing GPT-5.x using OpenRouter, OpenAI can't distinguish the people. It doesn't know if 1 person made all those requests, or N. 2. The ability to ensure your traffic is routed only to providers that claim not to log your inputs (not even for secur…

> It doesn't know if 1 person made all those requests, or N.

FWIW this is highly unlikely to be true.

It's true that the upstream provider won't know it's _you_ per se, but most LLM providers strongly encourage proxies like OpenRouter to distinguish between downstream clients for security and performance reasons.

For example:

- https://developers.openai.com/api/docs/guides/safety-best-pr...

- https://developers.openai.com/api/docs/guides/prompt-caching...

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#112

Post by NwtnsMthd »

Daviey wrote: post #60
ElFitz wrote: post #15

Has anyone (other than OpenClaw) used pi? ( https://shittycodingagent.ai/ , https://pi.dev/ ) Any insights / suggestions / best practices?

Reluctantly, the dev seems to have a stinky attitude. He went on an "OSS vacation", which is perfectly reasonable and said he'd be back on a certain date. I had a PR open for a trivial fix, someone asked when it would land. I shared he was still away. After his return I politely asked, "@badlogic hey, what can we do to progress this? Thanks x" I then got what I would consider an abusive reply, because he confused me…

But hey, the dev was generous to give it an MIT license, you could always just fork it and what you like ¯\_(ツ)_/¯

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#113

Post by nothinkjustai »

extr wrote: post #109

I think you are kidding if you think you are going to be remotely approximately the quantity/quality of output you get from a $100/max sub with Zed/Openrouter. I easily get $1K+ of usage out of my $100 max sub. And that's with Opus 4.6 on high thinking.

Not everyone is just vibecoding everything and relying on agents running sota models to do anything tho.

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#114

Post by lelanthran »

extr wrote: post #109

I think you are kidding if you think you are going to be remotely approximately the quantity/quality of output you get from a $100/max sub with Zed/Openrouter. I easily get $1K+ of usage out of my $100 max sub. And that's with Opus 4.6 on high thinking.

> I easily get $1K+ of usage out of my $100 max sub. And that's with Opus 4.6 on high thinking.

And people keep claiming the token providers are running inference at a profit.

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#115

Post by BeetleB »

napoleond wrote: post #111
BeetleB wrote: post #101

Earlier quoted context omitted.

The two things I like about OpenRouter: 1. The LLM provider doesn't know it's you (unless you have personally identifiable information in your queries). If N people are accessing GPT-5.x using OpenRouter, OpenAI can't distinguish the people. It doesn't know if 1 person made all those requests, or N. 2. The ability to ensure your traffic is routed only to providers that claim not to log your inputs (not even for secur…

> It doesn't know if 1 person made all those requests, or N. FWIW this is highly unlikely to be true. It's true that the upstream provider won't know it's _you_ per se, but most LLM providers strongly encourage proxies like OpenRouter to distinguish between downstream clients for security and performance reasons. For example: - https://developers.openai.com/api/docs/guides/safety-best-pr... - https://developers.opena…

Fair point. Would be good to hear from OpenRouter folks on how they handle the safety identifier.

For prompt caching, they already say they permit it, and do not consider it "logging" (i.e. if you have zero retention turned on, it will still go to providers who do prompt caching).

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#116

Post by gruez »

lelanthran wrote: post #114
extr wrote: post #109

I think you are kidding if you think you are going to be remotely approximately the quantity/quality of output you get from a $100/max sub with Zed/Openrouter. I easily get $1K+ of usage out of my $100 max sub. And that's with Opus 4.6 on high thinking.

> I easily get $1K+ of usage out of my $100 max sub. And that's with Opus 4.6 on high thinking. And people keep claiming the token providers are running inference at a profit.

>And people keep claiming the token providers are running inference at a profit.

Not everyone gets $1K of usage, and you don't know how fat the per-token margins are. It's like saying the local buffet place is losing money because you eat $100 worth of takeout for $30.

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#117

Post by zweicoder »

hayd wrote: post #96
ElFitz wrote: post #15

Has anyone (other than OpenClaw) used pi? ( https://shittycodingagent.ai/ , https://pi.dev/ ) Any insights / suggestions / best practices?

had been using claude max/opus with pi and the results have been incredible. Having pi write an AGENTS.md and dip your feet into creating your own skills specific to the project. With the anthropic billing change (not being able to use the max credits for pi) I think I have to cancel - as I'm whirring through credits now. Going to move to the $250/mo OpenAI codex plan for now.

I was looking into this as well since Claude models are costing too much with the Extra Usage changes.

Is OpenAI codex not also charging by usage instead of subscription when using pi?

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#118

Post by WhitneyLand »

>>For some reason Zed limits the Gemini 3.1 context to 200k tokens

It’s not just Zed, CoPilot also reduces the capabilities and options available when using models directly.

No thanks, definitely agree with the Open Router approach or native harness to keep full functionality.

Re: Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

#120

Post by pixel_popping »

senko wrote: post #94
pixel_popping wrote: post #81

Earlier quoted context omitted.

TOS says: access the Site or Service for purposes of reselling API access to AI Models or otherwise developing a competing service; So yes obviously you can do what you want as long as you abide by terms of service, but the terms of service does NOT allow you to resell the API.

> you aren't allowed to expose the access to end users, it has to be for internal usage only, > TOS says: access the Site or Service for purposes of reselling API access to AI Models or otherwise developing a competing service; I think what you meant is "you aren't allowed to expose the access to the API to end users", which is a fair condition IMHO. You're still allowed to expose the functionality (ie. build a SaaS…

To be clear, I like Openrouter and recommend it to many people (I don't aim to "shit on it").

It does talk about a competing service, if I build a service that propose all the image gen models of Openrouter, and charge the user for it per token, am I allowed?

Post reply on HN