Comment Comment by random17 These approaches, along with OpenRouter Fusion (https://openrouter.ai/blog/announcements/fusion-beats-fronti...) are different from ours in that:1. we trained custom models to predict LLM performance (this performs much better than asking LLMs directly to predict performance)2. we cut off model responses early if they are not performing well, saving on costs versus running them to completion3. finally we serve the unmodified output of the chosen model, instead of synthesizing the outputs into one, which makes us a model router parent random17 3 months ago
1. we trained custom models to predict LLM performance (this performs much better than asking LLMs directly to predict performance)
2. we cut off model responses early if they are not performing well, saving on costs versus running them to completion
3. finally we serve the unmodified output of the chosen model, instead of synthesizing the outputs into one, which makes us a model router