Live data from Hacker News

Gemini CLI

blog.google

141–150 of 820 posts

Re: Gemini CLI

#142

Earlier quoted context omitted.

AFAIK, Claude code operates on your subscription, no? That's what this support page says https://support.anthropic.com/en/articles/11145838-using-cla... Could have changed recently. I'm not a user so I can't verify.

In recent research (relying on Claude so bear that in mind), connecting CC via Anthropic Console account / API key ends up being less expensive.

There's a log analyzer tool that will tell you how much the API costs are for your usage: https://ccusage.com

Re: Gemini CLI

#143

I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a "Gemini Code Assist Standard or Enterprise" user to get additional usage. I didn't even know that existed! As a run of the mill Google user I get a generous usage tier but paying them specifically for "Gemini" doesn't get me anything when it comes to "Gemini CLI". Delightful!

Google is fumbling the bag so badly with the pricing. Gemini 2.5 Pro is the best model I've used (even better than o3 IMO) and yet there's no simple Claude/Cursor like subscription to just get full access. Nevermind Enterprise users too, where OpenAI has it locked up.

I wouldn't dream of thinking anyone has anything "locked up". Certainly not OpenAI which increasingly seems to be on an uphill battle against competitors (including Microsoft who even though they're a partner, are also a competitor) who have other inroads.

Not sure what you mean by "full access", as none of the providers offer unrestricted usage. Pro gets you 2.5 Pro with usage limits. Ultra gets you higher limits + deep think (edit: accidentally put research when I meant think where it spends more resources on an answer) + much more Veo 3 usage. And of course you can use the API usage-billed model.

Re: Gemini CLI

#144
post #89

Earlier quoted context omitted.

So, as a member of an organization who pays for google workspace with gemini, I get the message `GOOGLE_CLOUD_PROJECT environment variable not found. Add that to your .env and try again, no reload needed!` At the very least, we need better documentation on how to get that environment variable, as we are not on GCP and this is not immediately obvious how to do so. At the worst, it means that your users paying for gemi…

I believe Workspace users have to pay a separate subscription to use the Gemini CLI, the so-called “Gemini for Google Cloud”, which starts at an additional 19 dollars per month [^1]. If that’s really the case, it’s very disappointing to me. I expected access to Gemini CLI to be included in the normal Workspace subscription. [^1]: https://console.cloud.google.com/marketplace/product/google/...

Having played with the gemini-cli here for 30 minutes, so I have no idea but best guess: I believe that if you auth with a Workspace account it routes all the requests through the GCP Vertex API, which is why it needs a GOOGLE_CLOUD_PROJECT env set, and that also means usage-based billing. I don't think it will leverage any subscriptions the workspace account might have (are there still gemini subscriptions for workspace? I have no idea. I thought they just raised everyone's bill and bundled it in by default. What's Gemini Code Assist Standard or Enterprise? I have no idea).

Re: Gemini CLI

#145

I really wish these AI companies would STOP innovating until they work out how to let us “download all files” on the chat page. We are now three years into the AI revolution and they are still forcing us to copy and paste and click click crazy to get the damn files out. STOP innovating. STOP the features. Form a team of 500 of your best developers. Allocate a year and a billion dollar budget. Get all those Ai super s…

It seems you are still using the web interface.

When you hop over to platforms that use the API, the files get written/edited in situ. No copy/pasting. No hunting for where to insert edited code.

Trust me it's a total game changer to switch. I spent so much time copy/pasting before moving over.

Re: Gemini CLI

#146

> That’s why we’re introducing Gemini CLI Definitely not because of Claude Code eating our lunch!

Yea, i'm not even really interested in Gemini atm because last i tried 2.5 Pro it was really difficult to shape behavior. It would be too wordy, or offer too many comments, etc - i couldn't seem to change some base behaviors, get it to focus on just one thing. Which is surprising because at first i was ready to re-up my Google life. I've been very anti-Google for ages, but at first 2.5 Pro looked so good that i felt…

I've found that Gemini 2.5 Pro is pretty good at analyzing existing code, but really bad at generating a new code. When I use Gemini with Aider, my session usually went like:

    Me: build a plan to build X
    Gemini: I'll do A, B, and C to achieve X
    Me: that sounds really good, please do
    Gemini: 
    Me: no, please do B and C.
    Gemini: I apologize. 
    Me: no! A was already correct, please revert. Also do B and C.
    Gemini: 
Whereas Sonnet/Opus on average took me more tries to get it to the implementation plan that I'm satisfied with, but it's so much easier to steer to make it produce the code that I want.

Re: Gemini CLI

#147
post #75

Earlier quoted context omitted.

As a heavy Claude code user that's not really a selling point for me Ultimately quality wins out with LLMs. Having switched a lot between openai, google and Claude, I feel there's essentially 0 switching cost and you very quickly get to feel which is the best. So until Claude has a solid competitor I'll use it, open source or not

Even if you don't care about open source, you should care about all the obfuscation happening in the prompts/models being used by Cursor/Claude Code/etc. With everything hidden, you could be paying 200/mo and get served Haiku instead of Sonnet/Opus. Or you could be getting 1k tokens of your code inserted as context instead of 100k to save on inference costs.

so what? I care about the quality of the result. They can do that however they want

A more credible argument is security and privacy, but I couldn't care less if they're managing to be best in class using haiku

Re: Gemini CLI

#148
post #41

Hi - I work on this. Uptake is a steep curve right now, spare a thought for the TPUs today. Appreciate all the takes so far, the team is reading this thread for feedback. Feel free to pile on with bugs or feature requests we'll all be reading.

Thank you for your work on this. I spent the afternoon yesterday trying to convert an algorithm written in ruby (which I do not know) to vanilla JavaScript. It was a comedy of failing nonsense as I tried to get gpt-4.1 to help, and it just led me down pointless rabbit holes. I installed Gemini CLI out of curiosity, pointed it at the Ruby project, and it did the conversion from a single request, total time from "think I'll try this" to it working was 5 minutes. Impressed.

Re: Gemini CLI

#149

Ugh, I really wish this had been written in Go or Rust. Just something that produces a single binary executable and doesn't require you to install a runtime like Node.

This isn't about quality products, it's about being able to say you have a CLI tool because the other ai companies have one

Eh, I can't see how your comment is relevant ti the parent thread. Creating a CLI in Go is barely more complicated than JS. Rust, probably, but people aren't asking for that.

Re: Gemini CLI

#150
post #47

I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a "Gemini Code Assist Standard or Enterprise" user to get additional usage. I didn't even know that existed! As a run of the mill Google user I get a generous usage tier but paying them specifically for "Gemini" doesn't get me anything when it comes to "Gemini CLI". Delightful!

You don't get API keys for that subscription because it's a flat monthly cost.

That's not a given, Anthropic recently added Claude CLI access to their $20/m "Pro" plan removing the need for a separate API key.
Post reply on HN