I know lots of people use tokens to run coding agents, but I'm interested in hearing from people who are burning large amounts of tokens on automated tasks that aren't driving some kind of agent.
Do you have processes set up that are e.g. processing documents, audio, or video files? Particularly interested in hearing from people doing this in a business context.
We use a routing approach where simpler tasks go to smaller, cheaper models and more complex tasks go to frontier models. We are also working on having our own model for some of these workloads.
Document processing is probably one of our biggest agent use cases for tokens at this scale.