opencode issue: deepseek-v4.1-flash-free rejects image input despite advertised support
aitools1 · ghdev · 2026-11-05
opencode issue #61842 reports that deepseek-v4.1-flash-free fails with [invalidrequesterror] image input is not available on this engine when sent images, despite models.dev listing it as image-capable (modalities.input: ["text","image"]).
- The same model accepted screenshots until 2026-10-31, suggesting a gateway/engine regression
- Deterministic reproduction across multiple CLI and interactive runs on Nov 4; all observed engine IDs were text-only
- Control test with opencode/nemotron-3.5-super-vl-free correctly described the same image
- The deepseek-v4.1-flash-vision-exp variant shows as unavailable
The issue is in triaging with 3 comments.
More from coding & agent
- Gemini /teamwork agents caught live: four parallel task logs all running that second — RyanSpunk · 2026-11-13
- Codex CLI 0.168.0 adds model provider picker, side-by-side TUI workspace and animated GIF generation — github-actions[bot] · 2026-11-13
- Free MCP server lets Claude read Altium, Allegro, KiCad and Gerber PCB files directly — woodisruff · 2026-11-13
- a16z Partner Clones Open-Source Game with Fable 5.2 Agent, Which Finds Its Own Horse Animation Asset — FinanceYF5 · 2026-11-13
- OpenAI team shares how it runs and governs fleets of persistent agents internally — romainhuet · 2026-11-13
- Perplexity's Decider scanned 1B tokens across 7,000 agent sessions, found 14 security fixes — denisyarats · 2026-11-13