After pushing 2B tokens through DeepSeek V4.1 Flash, dev cuts AI bill from $300 to $30/month
gaganghotra_ · x · 2026-09-18
Developer @btsouth reports running 2+ billion tokens through DeepSeek V4.1 Flash in 4 days across his agent workflows. His monthly AI spend dropped from $300 — with constant usage-anxiety — to $30, letting him run agents all day without rationing tokens. He claims the model is remarkably close to frontier quality for his work, with no situation in 4 days of heavy use where he needed something better, and argues this isn't just a honeymoon period. His new stack: DeepSeek + OpenCode + Ollama Cloud, which he says has reset his expectations of what AI should cost. Note: the model name comes from a personal post and is not yet officially confirmed.
Related event: DeepSeek Flash Becomes Default Workhorse, Cutting AI Costs 90%(2 posts)→
More from coding & agent
- Tencent unveils Hyra 2.0, a research agent that builds reusable scientific tools — TencentHunyuan · 2026-11-02
- General Reasoning explains how to train agent swarms with RL and latency pressure — rosstaylor90 · 2026-11-02
- "Coding isn't the bottleneck anymore — usage windows are," says founder Kyle Gawley — kylegawley · 2026-11-02
- Demo passed ≠ production-ready: 5 questions to answer before letting agents run your business — _kellhus · 2026-11-02
- An AI agent passed 100 test chats—still not ready to run the business — djgoel123 · 2026-11-02
- Agent given total creative freedom produces a 1:44 code-drawn animated short film — ivegotnoidea1 · 2026-11-02