Skip to main content
TrueFoundry is an enterprise AI gateway that fronts 1000+ models across 40+ providers behind a single OpenAI-compatible endpoint. The gateway is OpenTelemetry-native: with a one-time configuration in the TrueFoundry dashboard, every request that flows through the gateway is exported to Arize AX as a trace — no application code or instrumentation required.
This page configures the gateway to export traces for all of its traffic. To instead instrument your own application’s calls to the gateway from Python, see the TrueFoundry LLM provider integration.

​
Launch Arize AX

To get started, sign up for a free Arize AX account. Then, from Settings → Service Keys, create a new API key with the Member role and copy your:
  • API Key (format ak-...)
  • Space ID (format U3BhY2U6...)

​
Configure trace export in TrueFoundry

In the TrueFoundry dashboard, navigate to AI Gateway → Controls → Settings → OTEL Config, then configure the OTLP exporter to point at Arize AX:
  1. Set Config Type to gRPC.
  2. Set the Traces Endpoint to otlp.arize.com:443.
  3. Add two gRPC metadata headers:
    • api_key — your Arize API Key
    • space_id — your Arize Space ID
  4. (Optional) Add resource attributes such as model_id to enrich your traces with identifying metadata.
  5. (Optional) Enable Exclude Request Data to omit request and response bodies if you don’t want prompt content sent to Arize.
  6. Click Save to activate automatic trace export.
The TrueFoundry OTEL configuration screen

​
Observe

Once configured, every request through the gateway is exported to Arize AX. In your Arize AX space, open the project for the tfy-llm-gateway service to see traces appear within ~30 seconds of activity. Each trace includes the model, prompt, response, token usage, and latency for the gateway request.

​
Resources

TrueFoundry Arize Integration Docs

TrueFoundry AI Gateway Documentation