381–390 of 493 posts
What I care about is whether the model is capable of the tasks I give it at the lowest cost. Right now I'm using Kimi-K3/GLM-5.2/Minimax. Sonnet is great but I burn through the tokens too fast. Opus 5 set to max is amazing and more intelligent than all of us. .998 of the time I don't need that kind of intelligence. I just need the job done.
Nice bicycle chain, the little basket with a fish didn't show up in the right place: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
For a while now, I've found pelican rendering to be an unreliable metric for LLM ability - and most people know it. Yet, somehow it gets upvoted to the very top of every new model discussion.
What I care about is whether the model is capable of the tasks I give it at the lowest cost. Right now I'm using Kimi-K3/GLM-5.2/Minimax. Sonnet is great but I burn through the tokens too fast. Opus 5 set to max is amazing and more intelligent than all of us. .998 of the time I don't need that kind of intelligence. I just need the job done.
Opus 5 fucking sucks to talk to and read compared to 5.6 Sol though. I’m fully done with Claude models until they figure this out
Why does this link to OpenRouter, which has no useful information on its own? Linking to the official API or the benchmarks would make more sense: - https://api-docs.deepseek.com/ - https://x.com/ChrisGPT/status/2087572834650407024/photo/1 (officially posted on WeChat, this is just one of many reposts)
I don’t know about you but I find the information about prices, effective price (weighted average), providers and performance, benchmarks (down bottom) very useful. With openrouter I can even test it right away and compare with other models (use the chat functions).
When GPT 6 comes out, would you expect the top thread to link to OpenRouter?
Even though cost-per-token is low, Deepseek v4 tends to burn an immense number of tokens to accomplish tasks.
Earlier quoted context omitted.
i dont see any price increase there... what am i missing?
It's a big confusion, some[0] say an email was sent about significant price increase, personal I haven't seen anything official [0] https://finance.yahoo.com/technology/ai/articles/deepseek-pl...
I read it as a "hey we will make stuff more expensive, don't miss it"
I am not sure what it is buy I suspect it might be GRPO.
Nice bicycle chain, the little basket with a fish didn't show up in the right place: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
So flash is 52 points on artificial analysis, and pro is 53
This was a disappointed to me. Why would I use pro over flash now? Is there some area where the difference is significant?
For tasks like pondering on something, reviewing code, etc. I use Pro, just because it feels like the right model for that.