Windsurf has a good free model. Good enough for autocomplete level work for sure (haven't tried it for more as I use Claude Code)
How I code with AI on a budget/free
21–30 of 251 posts
Re: How I code with AI on a budget/free
#22Re: How I code with AI on a budget/free
#23Windsurf has a good free model. Good enough for autocomplete level work for sure (haven't tried it for more as I use Claude Code)
Assuming you have to at least be logged into a windsurf account though?
Re: How I code with AI on a budget/free
#24[flagged]
You could get them all to idly chat to each other.
Re: How I code with AI on a budget/free
#25Re: How I code with AI on a budget/free
#26If you're looking for free API access, Google offers access to Gemini for free, including for gemini-2.5-pro with thinking turned on. The limit is... quite high, as I'm running some benchmarking and haven't hit the limit yet. Open weight models like DeepSeek R1 and GPT-OSS are also made available with free API access from various inference providers and hardware manufacturers.
I'm assuming it isn't sensitive for your purposes, but note that Google will train on these interactions, but not if you pay.
Re: How I code with AI on a budget/free
#27I wonder how much energy this is wasting.
Untradable carbon tax (or carbon price for people who hate the T word) is needed.
Re: How I code with AI on a budget/free
#28Earlier quoted context omitted.
Site really needs to drop the completely unreadable backup font.
Commenters need to stop complaining and hit the reader mode button on their browsers.
Not all browsers have a reader mode. And for the record I usually don’t like these design-related comments, but it was literally unreadable. Like some sort of 17th century chicken scratch cursive.
Re: How I code with AI on a budget/free
#29My experience lines up with the article. The agentic stuff only works with the biggest models. (Well, "works"... OpenAI Codex took 200 requests with o4-mini to change like 3 lines of code...) For simple changes I actually found smaller models better because they're so much faster. So I shifted my focus from "best model" to "stupidest I can get away with". I've been pushing that idea even further. If you give up on ag…
Aider as a non-agentic coding tool strikes a nice balance on the efficiency vs effectiveness front. Using tree-sitter to create a repo map of the repository means less filesystem digging. No MCP, but shell commands mean it can use utilities I myself am familiar with. Combined with Cerebras as a provider, the turnaround on prompts is instant; I can stay involved rather than waiting on multiple rounds of tool calls. It's my go-to for smaller scale projects.
Re: How I code with AI on a budget/free
#30To the OP: I highly recommend you look into Continue.dev and ollama/lmstudio and running models on your own. Some of them are really good at autocomplete-style suggestions while others (like gpt-oss) can reason and use tools. It's my goto copilot.
Same! I’ve been using Continue in VSCode and found most of the bigger Qwen models plus gpt-oss-120b to be great in agentic mode!