Syscovery Solve & Serve AI-Hub

Results 12 comments of Syscovery Solve & Serve AI-Hub

@djuillard the swagger simply indicates that the model should be used similarly as directly at Mistral, which isn't the case. Mistral definitely seems to do some preprocessing in terms of...

> [@blaesild](https://github.com/blaesild) Thanks for your feedback. We're planning some work to do to reduce token usage. Additionally, I'm going to make `gpt-4o-mini` the default for the MCP server. @danielchalef default...