Flash-Lite is a seriously good model. I have had zero structured calls fail with it as its cranking out obscene tok/s. If you can run with something that isn't quite bleeding edge smart, this model is gold.
Improved Gemini 2.5 Flash and Flash-Lite
211–220 of 285 posts
Re: Improved Gemini 2.5 Flash and Flash-Lite
#212Earlier quoted context omitted.
Granted, due to OpenRouter's 5.5% surcharge, any enormous whales have a strong financial incentive to use the provider's API directly. A "weekly active API Keys" faceted by models/app would be a useful data point to measure real-world popularity though.
They kinda have that already, no? https://openrouter.ai/apps?url=https%3A%2F%2Faider.chat%2F
I was skewing the Gemini starts with my Aider usage. Basically the only model in using with openrouter, until I recently started running qwen3-next locally.
2.5 is probably the best balance for tools like Aider.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#213Serious question: If it's an improved 2.5 model, why don't they call it version 2.6? Seems annoying to have to remember if you're using the old 2.5 or the new 2.5. Kind of like when Apple released the third-gen iPad many years ago and simply called it the "new iPad" without a number.
2.5 is not the version number, it's the generation of the underlying model architecture. Think of it like the trim level on a Mazda 3 hatchback. Mazda already has the Mazda 3 Sport in their lineup, then later they release the Mazda 3 Turbo which is much faster. When they release this new version of the vehicle its not called the Mazda 4... that would be an entirely different vehicle based on a new platform and powert…
Gonna steal this to help explain to non tech friends when it comes up again.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#214Earlier quoted context omitted.
Another issue: Gemini can’t do tool calling and (forced) json output at the same time If you want to use application/json as the specified output in the request, you can’t use tools So if you need both, you either hope it gives you correct json when using tools (which many times it doesn’t). Or you have to do two requests, one for the tool calling, another for formatting At least, even if annoying, this issue is pret…
Does any other provider allow that? what use cases are there for JSON + tool calling at the same time?
Please correct my likely misunderstanding here, but on the surface, it seems to me that "call some tools then return JSON" has some pretty common use cases.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#215Earlier quoted context omitted.
Another issue: Gemini can’t do tool calling and (forced) json output at the same time If you want to use application/json as the specified output in the request, you can’t use tools So if you need both, you either hope it gives you correct json when using tools (which many times it doesn’t). Or you have to do two requests, one for the tool calling, another for formatting At least, even if annoying, this issue is pret…
Does any other provider allow that? what use cases are there for JSON + tool calling at the same time?
OpenAI
Re: Improved Gemini 2.5 Flash and Flash-Lite
#216Serious question: If it's an improved 2.5 model, why don't they call it version 2.6? Seems annoying to have to remember if you're using the old 2.5 or the new 2.5. Kind of like when Apple released the third-gen iPad many years ago and simply called it the "new iPad" without a number.
It's pretty common to refer to models by the month and year they were released. For example, the latest Gemini 2.5 Flash is known as "google/gemini-2.5-flash-preview-09-2025" [1]. [1]: https://openrouter.ai/google/gemini-2.5-flash-preview-09-202...
If only there was some of versioning nomenclature they could use. Maybe even one that is … semantic? Oh how I wish someone would introduce something like this to the software engineering field. /s
In all seriousness though, their version system is awful.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#217Serious question: If it's an improved 2.5 model, why don't they call it version 2.6? Seems annoying to have to remember if you're using the old 2.5 or the new 2.5. Kind of like when Apple released the third-gen iPad many years ago and simply called it the "new iPad" without a number.
2.5 is not the version number, it's the generation of the underlying model architecture. Think of it like the trim level on a Mazda 3 hatchback. Mazda already has the Mazda 3 Sport in their lineup, then later they release the Mazda 3 Turbo which is much faster. When they release this new version of the vehicle its not called the Mazda 4... that would be an entirely different vehicle based on a new platform and powert…
I’d say it’s more like naming your Operating System off of the kernel version number.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#218Okay this is a nitpick but why wouldn't you increment a part of the version number to signify that there is an improvement? These releases are confusing.
Google has historically always made bad UX choices like this. Conway’s law definitely applies here. Too many different silos building every Google project.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#219Earlier quoted context omitted.
You should never argue with an LLM. Adjust the original prompt and rerun it.
While arguing may not be productive, I have had good results challenging Gemini on hallucinated sources in the past. eg, "You cited RFC 1918, which is a mistake. Can you try carefully to cite a better source here?" which would get it to re-evaluate, maybe by using another tool, admit the mistake, and allow the research to continue. With this example, several attempts resulted in the same thing: Gemini expressing a st…
One of the main problems with arguing with LLMs is your complaint becomes part of the prompt. Practically all LLMs have will take "don't do X" and do X, because part of "don't do X" is "do X," and LLMs have no fundamental understanding of negation.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#220Google seems to be the main foundation model provider that's really focusing on the latency/TPS/cost dimensions. Anthropic/OpenAI are really making strides in model intelligence, but underneath some critical threshold of performance, the really long thinking times make workflows feel a lot worse in collaboration-style tools, vs a much snappier but slightly less intelligent model. It's a delicate balance, because thes…
Agree, Gemini is soooooo freaking fast, but I rarely use it personally because Anthropic/OpenAI model have such a better output