... narrowed significantly over the past year. For prototyping or exploring a design, the $0.67 run is a good deal. For work requiring correctness and accuracy, Opus 4.7 remains ahead. Any experiences coding with open-weight models? [1]: MiniMax M2.7 vs. Claude Opus 4.6 Comment from fmerian(@fmerian): oss ftw Comment from Amit Raj(@amit_raj25): Is there any platform for renting GPU at reasonable price? Comment from Stan Kolotinskiy(@sk_uxpin): Given that I'm not trusting a LLM with ... ... from Stan Kolotinskiy(@sk_uxpin): @fmerian  hahaha, hard to disagree - especially for sensitive tasks Comment from Stan Kolotinskiy(@sk_uxpin): Interesting approach - I'm usually doing it the other way around: Sonnet/Opus for planning and then Kimi/Minimax (or Gemma/Qwen

... Hunters We just shipped Google Gemma 4 support, paired with our TurboQuant KV-cache compression engine. That means you can now run Google's any-to-any multimodal models directly inside your editor no API keys, no cloud, no data leaving your machine. What's new in this drop: Full Gemma