@googlecloud An orchestrator that picks the model is how more tokens get used. The GPUs still run them.
Reply to @googl | Hanami
@googlecloud An orchestrator that picks the model is how more tokens get used. The GPUs still run them.
Reply to @googlecloud: By selecting 'Auto' in the model picker, Gemini runs each job on the best-fit model orchestrating across Gemini and Claude models, and other leading private and open models in the future to deliver optimal quality and lower your cost.