Gemini 2.5 Flash
Google's fast, low-cost multimodal large language model in the Gemini 2.5 family.
HN commenters like it for low latency and low cost,1234 saying nothing in its price range matches its all-around performance.567 The main caveat is that Google is deprecating it,8 and one commenter finds the successor, Gemini 3 Flash, too expensive.9
Why people recommend it
Speed · 3
Commenters value its low latency and fast inference.
“I use Gemini-2.5-flash extensively, mostly for its low latency, and haven't found anything which works better at that speed/cost.”
“I used Gemini specifically because the inference speed is incredible”
Show 1 more
“I use Gemini 2.5 Flash for this and it's exceptionally good and fast as a HA assistant”
Price-performance · 3
Users say nothing at its price matches its overall performance.
“theres nothing in its price range that provides the same all around perf”
“I use Gemini-2.5-flash extensively, mostly for its low latency, and haven't found anything which works better at that speed/cost.”
Show 1 more
“Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers”
Beats Pro models · 2
Some found it as accurate as or better than Gemini Pro models while being faster.
“the pro was not noticeably more accurate, but significantly slower, so I used flash way more”
“2.5 flash works really well but 2.5 pro or 3.0 pro do a very poor job”
Image tasks · 2
It is recommended for image segmentation and praised for photo editing.
“we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5”
“2.5 flash works really well but 2.5 pro or 3.0 pro do a very poor job”
Voice use · 2
It is used for voice-to-text transcription and as a voice home assistant.
“get solid voice-to-text using Gemini 2.5 Flash”
“I use Gemini 2.5 Flash for this and it's exceptionally good and fast as a HA assistant”
Handles scale · 1
One company runs millions of requests a day through it.
“theres nothing in its price range that provides the same all around perf”
Caveats and dissent
Deprecation · 1
A commenter reports Google is removing the model.
“I use Gemini-2.5-flash extensively, mostly for its low latency, and haven't found anything which works better at that speed/cost.”
Costly successor · 1
One commenter says the replacement, Gemini 3 Flash, is expensive.
“theres nothing in its price range that provides the same all around perf”
Privacy · 1
As a cloud model, one commenter suggests it suits those less concerned about privacy.
“I use Gemini 2.5 Flash for this and it's exceptionally good and fast as a HA assistant”
Segmentation setup · 1
Google's docs recommend turning thinking off for image segmentation.
“we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5”
Often compared with
Who recommends it in their own words
Threads where it came up
- Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5 1 mention
- Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers 1 mention
- Show HN: Share your AI Setup, Learn from others 1 mention
- Don't discontinue Gemini 2.5 Flash 1 mention
- Ask HN: How are you using LLMs in production? 1 mention
- My Journey to a reliable and enjoyable locally hosted voice assistant 1 mention
Data: gemini-2-5-flash.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 11
“Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers”
“I use Gemini-2.5-flash extensively, mostly for its low latency, and haven't found anything which works better at that speed/cost.”
“fabric --model gemini-2.5-flash --pattern ask_ai”
“theres nothing in its price range that provides the same all around perf”
“Used LLMs: Gemini 2.5 Flash. ChatGPT 5”
“I use Gemini 2.5 Flash for this and it's exceptionally good and fast as a HA assistant”
“I used Gemini specifically because the inference speed is incredible”
“we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5”
“the pro was not noticeably more accurate, but significantly slower, so I used flash way more”
“get solid voice-to-text using Gemini 2.5 Flash”
“2.5 flash works really well but 2.5 pro or 3.0 pro do a very poor job”