Available via: Envoy AI Gateway’s OpenTelemetry tracing. This is not a Zespan SDK wrapper, see Send traces from any OTel-instrumented app for how the endpoint works.
AI_GATEWAY_TRACING_SEMCONV=gen_ai to switch to the GenAI names instead; Zespan reads both.
Setup
1
Set the exporter destination
Set
OTEL_EXPORTER_OTLP_ENDPOINT for the gateway to https://api.zespan.com and add the header x-api-key: zsp_... (OpenTelemetry’s OTEL_EXPORTER_OTLP_HEADERS). Confirm for your version that these standard variables apply, and which protocol it sends (JSON and protobuf are both accepted).2
Tell Zespan the source
Set the resource attribute
zespan.gateway to envoy, for example OTEL_RESOURCE_ATTRIBUTES=zespan.gateway=envoy. Without it the data is stored as plain OpenTelemetry: still readable, but its non-model spans are not marked as gateway spans.3
Verify
Send one request, then open Settings → Instrumentation → Gateway and OTLP data and press Refresh. See Instrumentation.
What gets captured
Attribute names come from Envoy AI Gateway’s published documentation and can change between versions. Use the Gateway and OTLP data card to see what actually arrives.
Gateway identity metadata is not stored. See AI gateways and Security.
Using the SDK too
Envoy AI Gateway does not document whether it continues an inboundtraceparent or exports the provider’s response id, so a call reported by both the SDK and this gateway may be counted twice. Use one of them for a given call. See Using the SDK too.
Next steps
- OTel integration, the endpoint, limits and attributes Zespan reads
- Instrumentation, check what arrived
- Kong AI Gateway, Bifrost, other gateways