DeepSeek V4.1 Flash gotcha: Pi agents need explicit "input": ["text", "image"] config
solyarisoftware · x · 2026-09-17
Blogger @xiaomovps shares a pitfall while wiring DeepSeek's new deepseek-v4.1-flash-expires-on-0910 (claimed native multimodal, faster, cheaper) into Pi Agent: despite hitting 300+ token/s, the model couldn't read images.
The cause: Pi only defaults to text input, so multimodal support requires explicitly setting "input": ["text", "image"]. Copying the old V4 config skipped this. He advises checking input types when adopting multimodal models and notes OpenRouter's model configs already flag Image inputs.
More from coding & agent
- Don't use an agent where a sequence works: the biggest AI-building mistake, per Hugo Bowne — hugobowne · 2026-09-17
- Plasma AI launches Radio: a shared chat room for Claude, Codex and Grok agents — rohanpaul_ai · 2026-09-17
- UIUC Launches Center for Orchestrated Agentic Biology to Study Brain Aging with Multi-Agent AI — dotey · 2026-09-17
- Dev uses LLMs to extract structured data from corporate financing documents — mayfer · 2026-09-17
- Open-source Claude skill builds MCP servers end-to-end via mcpfy SDK — ZealousidealTax42 · 2026-09-17
- First Jev test: 90% agreement with verified Gemini Flash workflow, not yet a drop-in replacement — CompleteSkeptic · 2026-09-17