[Inquiry]: MiniMax-M2.7-highspeed cannot do image analysis via the Anthropic API? #92
Description
Basic Information - Models Used
Minimax-M2.7-highspeed
Description
The core problem: Minimax subscription cannot do image analysis via the Anthropic API — that's a hard limitation on their end, confirmed by their own docs.
MiniMax M2.7 claimed that it is a multimodal model designed to handle images, along with text, audio, and video. It has advanced capabilities for interpreting and acting on visual data within agentic workflows.
Is there are solutions for us to have the Image / Vision support on Openclaw applications?