News for hackers. Stuff that matters.
Re:We're expanding our Gemini 2.5 family of models by zzleeper on Tuesday June 17, 2025 @01:38PM (#44301667)
Good luck using 2.5 for anything non-trivial.

I have about 500,000 news articles I am parsing. OpenAI models work well but found Gemini had fewer mistakes.

Problem is; they give me a terrible 10k RPD limit. To increase to the next tier, they then require a minimum amount of spending but I can't reach that amount even when maxing the RPD limit for multiple days in a row.

I emailed them twice and completed their forms but everyone knows how this works. So now I'm back at OpenAI, with a model with a bit more mistakes but that won't 403 me after half an hour of using it due to their limits.

Re:We're expanding our Gemini 2.5 family of models by be7a on Tuesday June 17, 2025 @04:10PM (#44303409)
The rate limits apply only to the Gemini API. There is also Vertex from GCP, which offers the same models (and even more, such as Claude) at the same pricing, but with much higher rate limits (basically none, as long as they don't need to cut anyone off with provisioned throughput iiuc) and with a process to get guaranteed throughput.
Re:We're expanding our Gemini 2.5 family of models by zzleeper on Tuesday June 17, 2025 @10:07PM (#44306037)
Had no idea... always thought Vertex was just a way to do enterprise offering!
Re:We're expanding our Gemini 2.5 family of models by eldenring on Tuesday June 17, 2025 @03:18PM (#44302814)
I'm guessing now that it is GA this won't be a problem.
Re:We're expanding our Gemini 2.5 family of models by zzleeper on Tuesday June 17, 2025 @03:54PM (#44303218)
I wish! The tier-based limits are still the same!

At least it's more expensive now so I guess I will be able to hop to the next tier sooner? ¯\_(ツ)_/¯