I've been using deepseek-v4-flash as a "worker" model with Claude Code to implement a tool using Rust/Iroh for my personal use, and it works fairly nicely when I use Opus as the planner/reviewer model. It seems to follow the plan generated by Opus, albeit with a few misses here and there that it cleans up later after being reviewed by Opus.

Fairly excited for the v4.1 launch. Input cache hit prices have been halved, which looks nice.

If you are okay with waiting use GLM 5.3 max. It costs more but still cheap. It is slow, but a very strong worker. Still dollars per day (at most) with heavy concurrent agent running. I load up planning and tasks in Opus or Sol, and just have glm flash workers go to town every night. My project has never advanced more smoothly.