←back to thread

Gemini CLI

(blog.google)
1342 points sync | 9 comments | 25 Jun 25 13:10 UTC | HN request time: 1.227s | source | bottom
Show context
iandanforth ◴[25 Jun 25 13:37 UTC] No.44377207[source]▶
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!
replies(21): >>44377223 #>>44377234 #>>44377268 #>>44377361 #>>44377524 #>>44377663 #>>44377759 #>>44377818 #>>44378537 #>>44378591 #>>44378915 #>>44379216 #>>44380359 #>>44382462 #>>44383491 #>>44384124 #>>44384673 #>>44384735 #>>44385178 #>>44385385 #>>44386691 #
behnamoh ◴[25 Jun 25 14:07 UTC] No.44377524[source]▶
Actually, that's the reason a lot of startups and solo developers prefer non-Google solutions, even though the quality of Gemini 2.5 Pro is insanely high. The Google Cloud Dashboard is a mess, and they haven't fixed it in years. They have Vertex that is supposed to host some of their models, but I don't understand what's the difference between that and their own cloud. And then you have two different APIs depending on the level of your project: This is literally the opposite of what we would expect from an AI provider where you start small and regardless of the scale of your project, you do not face obstacles. So essentially, Google has built an API solution that does not scale because as soon as your project gets bigger, you have to switch from the Google AI Studio API to the Vertex API. And I find it ridiculous because their OpenAI compatible API does not work all the time. And a lot of tools that rely on that actually don't work.

Google's AI offerings that should be simplified/consolidated:

- Jules vs Gemini CLI?

- Vertex API (requires a Google Cloud Account) vs Google AI Studio API

Also, since Vertex depends on Google Cloud, projects get more complicated because you have to modify these in your app [1]:

``` # Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values # with appropriate values for your project. export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT export GOOGLE_CLOUD_LOCATION=global export GOOGLE_GENAI_USE_VERTEXAI=True ```

[1]: https://cloud.google.com/vertex-ai/generative-ai/docs/start/...

replies(4): >>44377931 #>>44378027 #>>44378498 #>>44378744 #
1. tarvaina ◴[25 Jun 25 14:44 UTC] No.44377931[source]▶
It took me a while but I think the difference between Vertex and Gemini APIs is that Vertex is meant for existing GCP users and Gemini API for everyone else. If you are already using GCP then Vertex API works like everything else there. If you are not, then Gemini API is much easier. But they really should spell it out, currently it's really confusing.

Also they should make it clearer which SDKs, documents, pricing, SLAs etc apply to each. I still get confused when I google up some detail and end up reading the wrong document.

replies(4): >>44378649 #>>44380895 #>>44382672 #>>44388982 #
2. fooster ◴[25 Jun 25 15:48 UTC] No.44378649[source]▶
The other difference is that reliability for the gemini api is garbage, whereas for vertex ai it is fantastic.
replies(1): >>44381368 #
3. nprateem ◴[25 Jun 25 19:13 UTC] No.44380895[source]▶
Which would all be fine except some models like Imagen 4 only work on vertex.
4. nikcub ◴[25 Jun 25 20:09 UTC] No.44381368[source]▶
The key to running LLM services in prod is setting up Gemini in Vertex, Anthropic models on AWS Bedrock and OpenAI models on Azure. It's a completely different world in terms of uptime, latency and output performance.
replies(2): >>44383127 #>>44384669 #
5. happyopossum ◴[25 Jun 25 23:14 UTC] No.44382672[source]▶
> I think the difference between Vertex and Gemini APIs is that Vertex is meant for existing GCP users and Gemini API for everyone else

Nahh, not really - Vertex has a HUGE feature surface, and can run a ton of models and frameworks. Gemini happens to be one of them, but you could also run non-google LLMs, non LLM stuff, run notebooks against your dataset, manage data flow and storage, and and and…

Gemini is “just” an LLM.

6. shpat ◴[26 Jun 25 00:32 UTC] No.44383127{3}[source]▶
Have you had any luck getting your Claude quota bumped on Bedrock? I tried working through AWS support but got nowhere. Gave up and used Vertex + Gemini
7. com2kid ◴[26 Jun 25 06:18 UTC] No.44384669{3}[source]▶
Does OpenAI on azure still have that insane latency for content filtering? Last time I checked it added a huge # to time to first token, making azure hosting for real time scenarios impractical.
replies(1): >>44385890 #
8. shakna ◴[26 Jun 25 10:11 UTC] No.44385890{4}[source]▶
Yes.

Unless you convince MS to let you at the "Provisioned Throughput" model. Which also requires being big enough for sales to listen to you.

9. throwaway1550 ◴[26 Jun 25 16:35 UTC] No.44388982[source]▶
Ex-googler here. Google shipped their org hierarchy here.

Vertex API is managed by Vertex team in Google Cloud. This is a production ready infrastructure that is SRE managed but usually one or two steps from the bleeding edge.

Gemini API, Jules etc are built by Google Labs. This is close to the bleeding edge but not as production ready.