Please don't discontinue Gemini 2.5 Flash • Hacker News Board

Re: Please don't discontinue Gemini 2.5 Flash

#91

Post by duskdozer » Sat, Jul 11, 2026, 4:49 PM UTC

kilroy123 wrote: post #5

UGH why are they killing this model? This is one of the best models you can use in an API for a large swath of tasks. It's kind of the perfect trifecta of fast, cheap, and smart enough. Why does Google constantly kill off good things?

Somewhere along the line, killing the model or the "good things" is anticipated to make them more money than not doing so.

Re: Please don't discontinue Gemini 2.5 Flash

#92

Post by swe_dima » Sat, Jul 11, 2026, 9:37 PM UTC

3stacks wrote: post #88

swe_dima wrote: post #20

the writing is on the wall for it, I have switched to gemma-4-26b-a4b. At least in benchmarks, it scores higher and is faster.

How does it compare cost-wise for you?

About the same, using cloudflare. For some very bizarre reason Vertex has a very low non-adjustable quota.

Re: Please don't discontinue Gemini 2.5 Flash

#93

Post by Ferret7446 » Mon, Jul 13, 2026, 12:35 AM UTC

segmondy wrote: post #7

This is the problem with cloud models, you build a "predictable" workflow then they remove it with a new and improved one that is less deterministic and often costs more. If you use a local model discontinuation is no longer a thing to worry about.

That's the point, if you're using the weaker models, you should shift to a local model (it doesn't make sense for Google to keep providing it). SaaS is best for the SOTA models.