Cline's catalog refresh moves 44 providers' default model, most of them onto DeepSeek V4.1 Flash
GitHub·medium signal
v3.0.62 takes the bundled model catalog from 5,788 to 6,079 models and adds four providers: Infer by Flow7, Melious, NaN, and Wallaby. The release warns that the resolved default changes for 44 providers, most landing on DeepSeek V4.1 Flash, including Hugging Face, Fireworks, Requesty, Nebius, Cortecs, CrossModel, DigitalOcean, Eden AI and OpenCode Go, while Gemini and Vertex resolve to Gemini 3.8 Flash, GitHub Copilot and Vivgrid to GPT-6 Astra, and NVIDIA to GLM 5.3 Flash. If you use any provider without pinning a model, your agent quietly changes model on upgrade.