In the past weeks, Chinese AI labs have launched their new open-source models (Kimi K3, DeepSeek V4 Flash, Qwen 3.8 Max).
As these models topped charts with much lower costs, the notion that open-source models are just budget alternatives is being challenged. In this video, we
Qwen 3.8 Max vs GPT 5.6 Sol
“Whatever is frontier now…
Will become way way cheaper to run in 6 months.” Tibo is obviously right. 6 months ago Opus 4.6 was the SOTA frontier. Today you can run a 27B model (Qwen 3.8) on a gaming GPU that beats it on some of the coding benchmarks. Really great interview by
47 models at $0, no card, no subscription.
The bill arrives as tokens per second instead CDG wrote the setup honestly: one key, two minutes, any OpenAI compatible tool, and every model ending in -free costs nothing in either direction. The strongest line in it is that the same
You have reached the end of the archive
All of qwen38