muse-spark-1.2-contributor is my main model now, and I don't see that changing anytime soon. On price and capability combined, nothing else I've tried comes close at this point.
Meta trains on my data? Fine by me. Most of my projects are open source anyway.
Quick comparison vs DeepSeek:
- Muse Spark 1.2 (xhigh): intelligence index 57, multimodal
- DS V4 Pro 0813 (max): intelligence index 53, text only
Input: Muse $0.10 vs DS $0.66 off-peak / $1.32 peak
Output: Muse $0.20 vs DS $1.98 / $3.96
Cache: Muse $0.002 vs DS $0.022 / $0.044
Same ballpark capability, roughly 6-10x cheaper depending on what you're running.
