Check your fallback config: DeepSeek in Claude Code quietly burns tokens on V4-pro
AlchainHust · x · 2026-09-17
A practical heads-up: if you wire DeepSeek's API into Claude Code or similar agents, audit your model configs. The author found that despite switching the main model to V4.1-flash, stale fallback and subagent settings kept routing tokens to the pricier, worse-performing V4-pro, wasting money. Check main, fallback, and subagent model settings.
More from coding & agent
- Dev generates a full software promo video in pure code with GPT-6 Astra, no generative models — op7418 · 2026-09-17
- Frida, an iOS Personal Life Agent, Opens Second TestFlight Batch — Scobleizer · 2026-09-17
- Doubao Seed-2.1-pro-0915 hands-on: tool-calling score jumps 38.4% to 64.8%, coding cost down 40% — vista8 · 2026-09-17
- Dev claims harness makes agent computer use consume identical tokens to regular tool use — TejasKumar_ · 2026-09-17
- Spreadsheet agents should deliver editable drafts, not just approval summaries — Mountain_Athlete1350 · 2026-09-17
- Score Studio Launches as All-in-One Vision AI Platform for Annotation, Training and Deployment — markjeffrey · 2026-09-17