Skip to main content

Documentation Index

Fetch the complete documentation index at: https://agno-v2-shaloo-ai-support-link.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

When you run a team in Agno, the response you get (TeamRunOutput) includes detailed metrics about the run. These metrics help you understand resource usage (like token usage and time), performance, and other aspects of the model and tool calls across both the team leader and team members. Metrics are available at multiple levels:
  • Per-message: Each message (assistant, tool, etc.) has its own metrics.
  • Per-member run: Each team member run has its own metrics. You can make member runs available on the TeamRunOutput by setting store_member_responses=True,
  • Team-level: The TeamRunOutput aggregates metrics across all team leader and team member messages.
  • Session-level: Aggregated metrics across all runs in the session, for both the team leader and all team members.

​
Example Usage

Suppose you have a team that performs some tasks and you want to analyze the metrics after running it. Here’s how you can access and print the metrics: 
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.yfinance import YFinanceTools
from agno.utils.pprint import pprint_run_response
from rich.pretty import pprint

# Create team members
stock_agent = Agent(
    name="Stock Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Get stock prices and financial data.",
    tools=[YFinanceTools()],
)

# Create the team
team = Team(
    name="Finance Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[stock_agent],
    markdown=True,
    store_member_responses=True,
)

# Run the team
run_response = team.run(
    "What is the stock price of NVDA?"
)
pprint_run_response(run_response, markdown=True)

# Print team leader message metrics
print("---" * 5, "Team Leader Message Metrics", "---" * 5)
if run_response.messages:
    for message in run_response.messages:
        if message.role == "assistant":
            if message.content:
                print(f"Message: {message.content}")
            elif message.tool_calls:
                print(f"Tool calls: {message.tool_calls}")
            print("---" * 5, "Metrics", "---" * 5)
            pprint(message.metrics)
            print("---" * 20)

# Print aggregated team leader metrics
print("---" * 5, "Aggregated Metrics of Team", "---" * 5)
pprint(run_response.metrics)

# Print team leader session metrics
print("---" * 5, "Session Metrics", "---" * 5)
pprint(team.get_session_metrics().to_dict())

# Print team member message metrics
print("---" * 5, "Team Member Message Metrics", "---" * 5)
if run_response.member_responses:
    for member_response in run_response.member_responses:
        if member_response.messages:
            for message in member_response.messages:
                if message.role == "assistant":
                    if message.content:
                        print(f"Member Message: {message.content}")
                    elif message.tool_calls:
                        print(f"Member Tool calls: {message.tool_calls}")
                    print("---" * 5, "Member Metrics", "---" * 5)
                    pprint(message.metrics)
                    print("---" * 20)
You’ll see the outputs with following information:
  • input_tokens: The number of tokens sent to the model.
  • output_tokens: The number of tokens received from the model.
  • total_tokens: The sum of input_tokens and output_tokens.
  • audio_input_tokens: The number of tokens sent to the model for audio input.
  • audio_output_tokens: The number of tokens received from the model for audio output.
  • audio_total_tokens: The sum of audio_input_tokens and audio_output_tokens.
  • cache_read_tokens: The number of tokens read from the cache.
  • cache_write_tokens: The number of tokens written to the cache.
  • reasoning_tokens: The number of tokens used for reasoning.
  • duration: The duration of the run in seconds.
  • time_to_first_token: The time taken until the first token was generated.
  • provider_metrics: Any provider-specific metrics.

​
Developer Resources