LLM monitoring

The LLM (large language model) protocol graph lets you see the token rate for common LLMs, such as OpenAI, Ollama, and Gemini.

The following monitor is available from the LLM Graphs node:

Monitor	Description
LLM tokens per second	Monitors the number of LLM tokens that were received from the LLM engine per second, at any given time during the scenario run.

See also:

• LLM graphs
• LLM protocol
• Monitor and graph types
• View and customize online monitor graphs