To calculate token usage while using OpenAI's MultimodalAgent, you can track metrics such as prompt tokens, completion tokens, and total tokens. Below is an example Python snippet to help you monitor token usage:

from openai import MultimodalAgent

# Initialize your agent
agent = MultimodalAgent(api_key="your_api_key")

# Example input
input_data = "Your input text or multimodal data here"

# Process the input and get a response
response = agent.process(input_data)

# Access token usage metrics
token_usage = response["usage"]
print("Prompt tokens:", token_usage["prompt_tokens"])
print("Completion tokens:", token_usage["completion_tokens"])
print("Total tokens:", token_usage["total_tokens"])

This example assumes that the

response

object contains a

usage

field with token details. Let me know if you need further assistance! Sources: livekit.plugins.openai.realtime API documentation | livekit.agents.metrics API documentation