As we built our coding agent, we found that the biggest blocker was simply having enough tokens to do what you want to do. Our mission is to make the best open-source models as cheap and accessible as possible, especially super-capable agentic models. So, to kick it off, we’re selling a dollar for a dime – $50 gets you $500 in total credit. If there’s a lot of community interest I’d like to be able to do this more often, so please send any feedback you have, especially if you’re working on something interesting.
You're super right -- this is probably the one crack in our narrative and one that I sorely need to address. Hope to be back with something positive on this front soon, we're setting up all the benchmark harnesses to do this more equitably.
I think we have one on the site right now -- it's roughly 4.1-mini pricing. We're not aiming to make money off of individual users, which is why we're trialing a free thing (and trying to partner with open-source frameworks). Our bread and butter is more companies doing this at scale & licensing.
Yes, they can -- I actually tried a semantic edit implementation in Aider. It got the "correct edit format" percentage to 100%, but didn't really budge the overall percent correct on SOTA models. I should push it sometime, since it really helps the reliability of these local models like Qwen3. If you reach out to me, I can try to share some of this code with you as well (it needs to be cleaned up).
But yes, 1. have some code, 2. create a patch (semantic, diff, or udiff formats all work), and 3. apply will return it to you very fast. There's roughly a 10-15% merge error rate when we last benchmarked on using Claude 3.7 Sonnet to create diff patches, and with us it was 4%; and you can use the Apply as a backup if the merge fails.
-Preston and Eitan (pzhou@ and [email protected])