I m getting high prompt token counts

Are you using Simple context engine ? If not then it must be passing some similar records to LLM from your indexed documents. That is why token size is getting higher.

I'm using the standard query engine. is there a way to reduce the token count this way?

I'm assuming hello may not be part of your documents. So queries like greeting and conversations beyond the scope of documents will not be a good idea in here.

One way to reduce token count is to introduce similarity postprocessor: https://gpt-index.readthedocs.io/en/stable/core_modules/query_modules/node_postprocessors/usage_pattern.html#using-with-a-query-engine

But this could also make LLM to not generate anything in some cases.

yea @James_ws querying with "hello" is still going to pull relevant documents from the index. If you are trying to add normal chat interactions, you should probably use an agent
https://gpt-index.readthedocs.io/en/stable/examples/agent/openai_agent_with_query_engine.html