Hugging Face Inference Providers

Hugging Face Inference Providers routes model calls across hosted providers through a unified API, including an OpenAI-compatible endpoint at https://router.huggingface.co/v1. Use the OpenAI Python client with your Hugging Face token and Arize AX captures requests through openinference-instrumentation-openai.

This page instruments the OpenAI-compatible Hugging Face router. It is separate from the Hugging Face smolagents integration, which instruments agent framework spans.

Prerequisites

Python 3.9+
An Arize AX account (sign up)
A Hugging Face token with Inference Providers access

Launch Arize

Sign in to your Arize AX account.
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="hugging-face-inference-providers-tracing-example"
export HF_TOKEN="<your-hugging-face-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 Hugging Face Inference Providers.")

Run Hugging Face Inference Providers

# 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

client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=os.environ["HF_TOKEN"],
)

response = client.chat.completions.create(
    model="openai/gpt-oss-20b",
    messages=[
        {
            "role": "user",
            "content": "Give one reason to monitor model provider latency.",
        },
    ],
)

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

Expected output

Arize AX tracing initialized for Hugging Face Inference Providers.
Monitoring model provider latency helps teams detect slowdowns, compare providers, and understand how inference speed affects user experience.

Verify in Arize

Open your Arize AX space and select project hugging-face-inference-providers-tracing-example.
You should see a new trace within ~30 seconds containing a ChatCompletion LLM span with prompt, response, model, token, and latency metadata.
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)
AX CLI
SDK

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.

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.

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

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"
)

// Reads ARIZE_API_KEY from the environment.
import { listSpans } from "@arizeai/ax-client";

const { data: spans } = await listSpans({
  project: process.env.ARIZE_PROJECT_NAME!,
  space: process.env.ARIZE_SPACE_ID!,
  limit: 5,
});
const count = spans.length;
console.log(
  count ? `${count} span(s) found` : "No spans yet — recheck setup",
);

client, err := arize.NewClient(
    arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
)
if err != nil {
    log.Fatal(err)
}
resp, err := client.Spans.List(ctx, spans.ListRequest{
    Project: os.Getenv("ARIZE_PROJECT_NAME"),
    Space:   os.Getenv("ARIZE_SPACE_ID"),
    Limit:   5,
})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("%d span(s) found\n", len(resp.Spans))

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.
Hugging Face spans missing but other spans present. OpenAIInstrumentor().instrument(...) must run before any import openai.
401 from Hugging Face. Use your Hugging Face token, not your OpenAI or Arize API key.
Model not found. Replace the model with one available through Hugging Face Inference Providers. Some models require selecting a provider or accepting model terms before use.

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Evaluation