Prompt processing statistics

[SurealCereal]

Is it possible to show response processing statistics, like tokens per second? I have not been able to find anything in the docs or issues.

[SurealCereal]

I don't see any statistics being parsed from responses in OpenAIClient.js, also used for Ollama, which I am using locally. The OpenAI docs don't mention anything about stats, so I expect they would have to be generated based upon the token count and generation time. I did a cursory search of the source code and did not find anything obvious.

Here is an example of what I'd like to see. Tokens/second at the very least.