DeepSeek V4 Flash Free Capped at 200K Context in OpenCode Metadata Bug Report
abhisheksharma611 · ghdev · 2026-08-07
A developer filed a bug report on the OpenCode Zen platform revealing that the DeepSeek V4 Flash Free model is incorrectly capped at a 200K context window in the models.dev metadata, despite natively supporting 1M tokens.
This configuration issue forces new users into a lower default limit and triggers premature context compression. While users can manually override this by editing their opencode.json file, the developer requests a server-side metadata update to align the free tier's default with the model's official capabilities.
More from coding & agent
- Opus 5.5 + Three.js demo stuns with water physics, fish and blossoms — nikola_mr64990 · 2026-10-16
- Grok-built linear regression bot claims $508K PnL in 125 days on Polymarket — Roger_M_Taylor · 2026-10-16
- Karpathy's knowledge engine workflow: Claude Code turns raw notes into a self-updating wiki — nikola_mr64990 · 2026-10-16
- Sierra and Meta unveil Personal Agent Protocol with Zapier as launch partner — sujingshen · 2026-10-16
- ArcKit adds 102 AI-narrated short films for commands across 14 community overlays — mcraddock · 2026-10-16
- Personal agents live or die on chaining tasks, not single-task ability — sujingshen · 2026-10-16