TrueFoundry

Trace TrueFoundry AI Gateway calls with OpenInference and send spans to Arize AX for LLM observability.

TrueFoundry is an enterprise AI gateway — one OpenAI-compatible endpoint that fronts 1000+ models across 40+ providers (OpenAI, Anthropic, Bedrock, Vertex AI, Mistral, and more) with governance, budgets, and guardrails. The endpoint at https://gateway.truefoundry.ai mirrors OpenAI’s schema, so any OpenAI client works with base_url set to the gateway. Arize AX captures every gateway call via the openinference-instrumentation-openai package — the same instrumentor that covers OpenAI’s hosted API.

This guide instruments your application’s calls to the gateway. TrueFoundry can also export traces for every gateway request to Arize directly, with no application code — see the TrueFoundry platform integration.

Prerequisites

• Python 3.9+
• An Arize AX account (sign up)
• A TRUEFOUNDRY_API_KEY — a Personal Access Token or Virtual Account Token from the Access section of TrueFoundry

Launch Arize

1. Sign in to your Arize AX account.
2. From Space Settings, copy your Space ID and API Key. You will set them as ARIZE_SPACE_ID and ARIZE_API_KEY below.

Install

pip install arize-otel openinference-instrumentation-openai openai

Configure credentials

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="truefoundry-tracing-example"
export TRUEFOUNDRY_API_KEY="<your-truefoundry-token>"

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for TrueFoundry.")

Run TrueFoundry

# example.py

# Importing instrumentation first ensures tracing is set up
# before `openai` is imported.
from instrumentation import tracer_provider

import os

from openai import OpenAI

# Point the OpenAI client at the TrueFoundry AI Gateway endpoint.
client = OpenAI(
    base_url="https://gateway.truefoundry.ai",
    api_key=os.environ["TRUEFOUNDRY_API_KEY"],
)

response = client.chat.completions.create(
    # Models use a `provider-account/model-name` format — the prefix is the
    # provider account configured in your TrueFoundry workspace.
    model="openai/gpt-4.1-mini",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)

print(response.choices[0].message.content)

Expected output

Arize AX tracing initialized for TrueFoundry.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.

Verify in Arize

1. Open your Arize AX space and select project truefoundry-tracing-example.
2. You should see a new trace within ~30 seconds containing a ChatCompletion LLM span with the prompt, response, and token usage attached. The model name on the span will be the resolved model the gateway routed to (e.g. gpt-4.1-mini-2025-04-14).
3. If no traces appear, see Troubleshooting.

Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

Arize skill (agent)

Install the Arize Skills plugin and let your coding agent check for you:

npx skills add Arize-ai/arize-skills

Then prompt your agent:

Use the arize-trace skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.

AX CLI

Export recent spans for your project — any rows mean traces are landing:

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

A non-zero count confirms spans reached Arize AX. Run ax auth login first if you have not authenticated. See the ax spans reference.

SDK

Query the project’s spans and check that at least one came back.

Python

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

SDK span references: Python · TypeScript · Go.

Troubleshooting

• No traces in Arize. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs example.py. Enable OpenTelemetry debug logs with export OTEL_LOG_LEVEL=debug and re-run.
• TrueFoundry spans missing but other spans present. OpenAIInstrumentor().instrument(...) must run before any import openai. Make sure instrumentation.py is the first import in your entry point.
• 401 from TrueFoundry. Use a TrueFoundry token (Personal Access Token or Virtual Account Token from the Access section), not your OpenAI key. Pass it as the api_key — the OpenAI client sends it as a Bearer token.
• Model not found. Use the provider-account/model-name identifier from your gateway (e.g. openai/gpt-4.1-mini). The prefix is the provider account name configured in your TrueFoundry workspace, not a fixed value — copy the exact model ID from the Playground Code Snippets tab.

Resources

TrueFoundry AI Gateway Documentation

OpenInference OpenAI Instrumentor (used for TrueFoundry)

TrueFoundry AI Gateway