Gemini 2.0 isn't particularly great at coding. The Gemini 1206 preview that was released just before 2.0 is quite good, though. Still, it hasn't taken the crown from Claude 3.5 Sonnet (which appears to now be tied with o1). Very much agree about Cline + VSCode, BTW. My preferred models with Cline are 3.5 Sonnet and 3.5 Haiku. I can throw the more complex problems at Sonnet and use Haiku for everything else.
In the wake of the o1 release, and with the old aider benchmark saturating, Paul from aider has created a new, much harder benchmark. o1 dominates by a substantial margin.
the context limits on google are nuts! Being able to pump 2 million tokens in and having it cost $0 is pretty crazy rn. Cline makes it seamless to switch between APIs and isnt trying to shoehorn their SAAS AI into a custom vscode (looking at you cursor)
> When you use Unpaid Services, including, for example, Google AI Studio and the unpaid quota on Gemini API, Google uses the content you submit to the Services and any generated responses to provide, improve, and develop Google products and services and machine learning technologies, including Google's enterprise features, products, and services, consistent with our Privacy Policy.
Google inference is a lot cheaper since they have their own hardware so they don't have to pay licensing to NVIDIA, thus their free tier can give you much more than others.
Other than that the catch is like all other free tiers, it is marketing and can be withdrawn at any moment to get you to pay after you are used to their product.
There are a lot of tools, but only a small pool of tools that are worth checking out. Cline, Continue, Windsurf, CoPilot, Cursor, and Aider are the ones that come to mind.
