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.

Original post →

More from coding & agent

coding & agent channel →