I use these guys. https://crof.ai/tos. Their prices match deepseek, pretty dang fast, and support ZDR. Maybe they serve quantized models but I havent seen a drop in quality from my evals using them vs Deepseek or even for other models.
I’ve unfortunately had to temper my excitement with Cognition’s models/products given the amount of unwarranted hype they created with Devin on first release, but hopefully this is good.
It was a rough heuristic for how much more opus/5.5 would presumably cost if you extrapolate from glm5.2 prices. In any case input tokens for 5.4/4.6 are 70-100% more expensive, cached about 3-100%, and output tokens anywhere from 60%-240% more as per all their current api pricing. I highly doubt 5.4/4.6 are that much more expensive to serve given how cheap and commoditized inference has become, and how comparable they are perfomance wise.
You can make a fairly decent assumption by calculating the margin on serving glm 5.2, and adding say 30% extra costs and it still leaves a healthy margin
I dont think that’s accurate. I mean look at how much more expensive frontier closed source models are vs something like glm 5.2 which is just about as good. Serving glm is really cheap, and high margin. Obviously no one knows, just how much their inference costs, but if we assume that opus/gpt are maybe 15-20% more parameters than glm 5.2, then it makes no sense for them to charge almost much much more than glm
Personally, I disable pre-commit hooks because they’re annoying and slow me down. Pre-push hook would make more sense. Secondly, i’d ideally want to use my codex/ claude subs for this, not an api key
I use OMP. Was on Pi but switched over because I like OMP's subagents implementation. Use 5.5/4.8 for coming up with a very detailed plan, ds4pro/mimo for implementation of easy features, 5.5/4.6 for larger/harder features, and 5.5/4.6 for a review. I use them in onorca.dev(settled here after trying just about any "agent ade". i also sometimes use Zed as well. I'm curious to know if folks use any meta-harnesses?
How do you a) share context/chat etc with each other? plugin? have them make a file? Why did you opt for either of them instead of something like opencode that supports those models?
I hope they bring it to their apis, especially v4flash. I find myself using mimo 2.5 more since it supports vision and makes it cheap for doing e2e tests with playwright or similar
Have you tried glm 5.2? It’s better than ds4pro and very close to opus4.6. Alot more expensive than ds4pro/mimo but significantly chesper than opus 4.6 for 90% of the quality
Deepseek direct is atleast 2x cheaper than other providers serving it. Maybe their caching strategy is just significantly better or they’re subsidizing api pricing. I think it’s the former. $2 is closer to 50 million v4pro tokens in my experience
What are interesting problems? Deepseek and some other open source models do decently well in the gpu kernel benches. https://kernelbench.com/hard Most people think they’re working on “very hard” problems and they really aren’t