Trying to track which agentic tools (both IDEs and CLIs) give free access to pro-grade LLMs (Claude Sonnet/Opus 4, Gemini 2.5 Pro, Grok 4, OpenAI o3, etc). May be gaps or mistakes - feedback welcome.

My Gemini CLI quota for Gemini 2.5 Pro gets used up way faster than the ~100 h/day math. I’m seeing <1 hour of coding before it auto-switches to Flash. Anyone else experiencing it?

I haven’t personally run into the fallback to Flash (probably because I mostly use Claude Code now). Curious if others using Gemini CLI are seeing the same: does the switch to Flash happen after less than an hour of coding with Gemini 2.5 Pro? Going to dig a bit and see if this is a common pattern.

Yes, it does switch in less than an hour.

Add Warp https://www.warp.dev/pricing

Thanks, added Warp to the list with the following data:

Up to 150 AI requests/month → about 15 coding hours/month (assuming 10 req/hour) with frontier models. The Free plan explicitly supports frontier models like Claude Sonnet 4, OpenAI o3, and Gemini 2.5 Pro.

That puts Warp at #2 on the list, right below Gemini CLI.

I believe Warp can count a typical agent call as more than 1 request. Worth trialing how many that actually is in practice.