News for hackers. Stuff that matters.
Re:Gemini 2.5 Flash by 42lux on Thursday April 17, 2025 @03:44PM (#43721284)
The API is free, and it's great for everyday tasks. So yes there is no better bang for the buck.
Re:Gemini 2.5 Flash by drusepth on Thursday April 17, 2025 @03:47PM (#43721312)
Wait, the API is free? I thought you had to use their web interface for it to be free. How do you use the API for free?
Re:Gemini 2.5 Flash by dcre on Thursday April 17, 2025 @03:50PM (#43721366)
You can get an API key and they don't bill you. Free tier rate limits for some models (even decent ones like Gemini 2.0 Flash) are quite high.

https://ai.google.dev/gemini-api/docs/pricing

https://ai.google.dev/gemini-api/docs/rate-limits#free-tier

Re:Gemini 2.5 Flash by NoahZuniga on Thursday April 17, 2025 @05:01PM (#43722170)
The rate limits I've encountered with free api keys has been way lower than the limits advertised.
Re:Gemini 2.5 Flash by jmacd on Thursday April 17, 2025 @07:35PM (#43723393)
I agree. I found it unusable for anything but casual usage due to the rate limiting. I wonder if I am just missing something?
Re:Gemini 2.5 Flash by tempthrow on Friday April 18, 2025 @04:08AM (#43726020)
I think it's the small TPM limits. I'll be way under the 10-30 requests per minute while using Cline, but it appears that the input tokens count towards the rate limit so I'll find myself limited to one message a minute if I let the conversation go on for too long, ironically due to Gemini's long context window. AFAIK Cline doesn't currently offer an option to limit the context explosion to lower than model capacity.
Re:Gemini 2.5 Flash by nolok on Friday April 18, 2025 @02:48AM (#43725642)
I'm pretty sure that's a google maps' level of free where once in control they will massively bill it
Re:Gemini 2.5 Flash by dcre on Friday April 18, 2025 @08:44AM (#43727535)
There is no reason to expect the other entrants in the market to drop out and give them monopoly power. The paid tier is also among the cheapest. People say it’s because they built their own their inference hardware and are genuinely able to serve it cheaper.
Re:Gemini 2.5 Flash by spruce_tips on Thursday April 17, 2025 @03:49PM (#43721345)
create an api key and dont set up billing. pretty low rate limits and they use your data
Re:Gemini 2.5 Flash by midasz on Thursday April 17, 2025 @04:03PM (#43721550)
I use Gemini 2.5 pro experimental via openrouter in my openwebui for free. Was using sonnet 3.7 but I don't notice much difference so just default to the free thing now.
Re:Gemini 2.5 Flash by mlboss on Thursday April 17, 2025 @03:49PM (#43721344)
using aistudio.google.com