I’d agree to Opus 5.5 but deepseek is pretty close to all other models imo

does the gap feel that big in coding though? curious if it's closer in agent harnesses than what this index says

sol at 55 for $1.27 a task vs $10.04 for opus max is not to bad for the price!

Excited to follow this along!

Dude. Unreal. How many iterations did it take to get to this level?

nice! finally, no more saving and reuploading screenshots just to share someone's chart

keen to see where deepseek flash lands at that price. cheap models doing well on memory would be a big deal for agents

and the agent that wrote it doesn't know either haha

build your own?

basically free in codex is a pretty good deal to be complaining about haha. i love using it for computer use

several questions on one card is a nice touch, my tweet drafting bot asks me way too many one at a time haha

how good - gonna experiement with this same setup myself. How do you wire in deepseek to claude code?

1M daily in 2 weeks is such a good achievement. the free models are a big part of why i keep using it! nice work team

keen to see this. whats the metric it's climbing?

do it. i only run 4 @bot (one plans my bike rides, one writes my drafts) and 50 sounds like running a whole company haha

which open model are you actually waiting on glm 5.5 flash qwen 4 27b kimi k4 something else (say below) mine: Fable 5.5!

Im losing my mind. We need fable 5.5

Hey @AmpCode just pinging this to you guys

Damn, is this is true then it might explain my usage dropping quicker in @AmpCode

I’m hoping it’ll be free in OpenCode 😅