Distributed tracing

Every request in your AI application is captured as a trace: a tree of spans representing every step in the execution chain. Each span carries its input, output, latency, token counts, and status.

Traces are collected using OpenTelemetry and are supported across Mistral products and the Mistral SDK.

In this section

• Send traces: instrument your application and start collecting trace data.
• Explore traces: search, filter, and inspect traces in Studio.
• Data redaction: review and configure what is masked before spans are exported.