Capturing Metrics
Capture AI metrics from Azure OpenAI calls in Statsig, including latency, cost, token usage, and per-prompt success signals for evaluation.
The Azure AI SDK automatically captures relevant invocation and usage metrics from each API call and logs them to Statsig. These events stream in real time in the console at https://console.statsig.com/metrics/events.
Metrics captured
Completion invocations capture the following metrics automatically: completion token length, prompt token length, latency, model name, total token length.
For example, a completion API call results in a usage log that looks like this:
You can use these metrics to compare multiple deployments and run experiments against different parameter sets, helping optimize cost, responsiveness, and user experience.
Was this helpful?