Run metrics

Every ask() returns RunResult.metrics and trace fields for cost, latency, tokens, cache hit, and request_id.

python

result = ts.ask("Generate a one-paragraph incident summary.", provider="openai", model="gpt-4o")

print(result.text)

print("cost_usd:", result.metrics.cost_usd)

print("latency_ms:", result.metrics.latency_ms)

print("tokens_input:", result.metrics.tokens_input)

print("tokens_output:", result.metrics.tokens_output)

print("tokens_total:", result.metrics.tokens_total)

print("tokens_saved:", result.metrics.tokens_saved)

print("savings_ratio:", result.metrics.savings_ratio)

print("request_id:", result.trace.request_id)

print("history_mode:", result.context.history_mode)