> ## Documentation Index
> Fetch the complete documentation index at: https://www.getmaxim.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Custom Metrics

> Learn how to track and log metrics from LLM generations, traces, retrievals, and sessions in your AI application. Monitor performance, quality, and resource usage by tracking trace-level metrics like tool call counts, costs, and evaluation scores.

## Track Metrics in Traces

Track trace-level metrics like tool call counts, costs, and evaluation scores.

<CodeGroup>
  ```typescript JS/TS theme={null}
  const trace = logger.trace({
      id: "trace-id",
      name: "customer-query-processing",
  });

  // Track metrics
  trace.addMetric('tool_calls_count', 3);
  trace.addMetric('cost_usd', 0.05);
  trace.addMetric('tokens_total', 1420);
  trace.addMetric('user_feedback_score', 4.7);
  ```

  ```python Python theme={null}
  from maxim.logger import TraceConfig

  trace = logger.trace(TraceConfig(
      id="trace-id",
      name="customer-query-processing",
  ))

  # Track metrics
  trace.add_metric('tool_calls_count', 3)
  trace.add_metric('cost_usd', 0.05)
  trace.add_metric('tokens_total', 1420)
  trace.add_metric('user_feedback_score', 4.7)
  ```
</CodeGroup>

## Track Metrics in Generations

Track generation quality metrics, token accounting, and streaming characteristics for LLM calls.

<CodeGroup>
  ```typescript JS/TS theme={null}
  // Create generation object
  const generation = trace.generation({
      id: "generation-id",
      name: "customer-support--gather-information",
      // Additional fields
  });

  // Track metrics
  generation.addMetric('tokens_in', 312);
  generation.addMetric('tokens_out', 87);
  generation.addMetric('output_tokens', 87);
  generation.addMetric('ttft_ms', 180.5);
  generation.addMetric('tps', 15.8);
  generation.addMetric('avg_logprob', -0.32);
  ```

  ```python Python theme={null}
  from maxim.logger.components.generation import GenerationConfig

  # Create generation object
  generation = trace.generation(GenerationConfig(
      id="generation-id",
      name="customer-support--gather-information",
      # Additional fields
  ))

  # Track metrics
  generation.add_metric('tokens_in', 312)
  generation.add_metric('tokens_out', 87)
  generation.add_metric('output_tokens', 87)
  generation.add_metric('ttft_ms', 180.5)
  generation.add_metric('tps', 15.8)
  generation.add_metric('avg_logprob', -0.32)
  ```
</CodeGroup>

<Note>
  Learn how to track complete LLM flows in the [LLM logging guide](/tracing/tracing-via-sdk/generations).
</Note>

## Track Metrics in Retrievals

Track RAG evaluation metrics like precision, recall, MRR, and NDCG for retrieval operations.

<CodeGroup>
  ```typescript JS/TS theme={null}
  const retrieval = trace.retrieval({
      id: "retrieval-id",
      name: "knowledge-base-search",
  });

  // Track metrics
  retrieval.addMetric('precision', 0.82);
  retrieval.addMetric('recall', 0.76);
  retrieval.addMetric('mrr', 0.61);
  retrieval.addMetric('results_count', 10);
  ```

  ```python Python theme={null}
  from maxim.logger import RetrievalConfig

  retrieval = trace.retrieval(RetrievalConfig(
      id="retrieval-id",
      name="knowledge-base-search",
  ))

  # Track metrics
  retrieval.add_metric('precision', 0.82)
  retrieval.add_metric('recall', 0.76)
  retrieval.add_metric('mrr', 0.61)
  retrieval.add_metric('results_count', 10)
  ```
</CodeGroup>

<Note>
  Explore more on retrieval tracking in the [Retrieval logging guide](/tracing/tracing-via-sdk/retrieval).
</Note>

## Track Metrics in Sessions

Track session-level aggregates like trace counts and message counts.

<CodeGroup>
  ```typescript JS/TS theme={null}
  const session = logger.session({
      id: "session-id",
      name: "user-conversation",
  });

  // Track metrics
  session.addMetric('traces_count', 4);
  session.addMetric('user_messages_count', 2);
  session.addMetric('assistant_messages_count', 2);
  ```

  ```python Python theme={null}
  from maxim.logger import SessionConfig

  session = logger.session(SessionConfig(
      id="session-id",
      name="user-conversation",
  ))

  # Track metrics
  session.add_metric('traces_count', 4)
  session.add_metric('user_messages_count', 2)
  session.add_metric('assistant_messages_count', 2)
  ```
</CodeGroup>

<img src="https://mintcdn.com/maximai/LMA67PoeLl5v8ibw/images/docs/tracing/via-sdk/custom-metrics.png?fit=max&auto=format&n=LMA67PoeLl5v8ibw&q=85&s=7344c929a3255fdde35c165710549fa7" alt="Metrics" width="2990" height="1710" data-path="images/docs/tracing/via-sdk/custom-metrics.png" />