With Cline + Gemini 2.5 Pro, one can get the exact same feature set that Cursor and Windsurf provide. They only call the APIs of the big LLM Providers without an advanced secret sauce.
It‘s even the opposite - they worsen model performance by limiting context size. The key advantage, the fixed monthly costs instead of variable API usage, is now gone with Gemini 2.5 Pro…
What is left that justifies their ridiculous valuation atm?
That’s an interesting question, they do have quite a few premade prompts and domain experience which cline may or may not have exact matches of
I find claude-code a more interesting example of a cursor killer, but the unlimited context size ramps up costs tremendously.
I agree that Claude Code is amazing. But before Gemini 2.5 Pro (after Claude Code), I would use Cursor for lightweight tasks to save costs and Claude Code when it was really necessary.
20$ is what you can easily end up spending in a single day of Claude Code. But Gemini 2.5 Pro combines the advantages of both imo
After your post I went and tried it today, in my tests on a medium sized repo cline actually killed it, very similar performance to cursor. Roo code was slightly better for me compared to cline, both roo code and cursor landed some acceptable changes in an existing repo with the same prompt, about 300ish lines of code. I used anthropic for everything for an apples to apples comparison, will try out gemini this week.
I’d love to see somebody do a price breakdown of a full month of constant use for both systems.
I think it really makes sense to use Gemini. It is COMPLETELY free. No variable costs for now. I experienced comparable performance to Claude 3.5/3.7.