Z.ai

Z.ai provides GLM models through an API compatible with the OpenAI SDK. Set the OpenAI client’s base_url to Z.ai and use openinference-instrumentation-openai to send LLM traces to Arize AX.

This page instruments OpenAI SDK calls to Z.ai’s OpenAI-compatible endpoint. It is not a separate Z.ai-specific OpenInference instrumentor.

Prerequisites

Python 3.9+
An Arize AX account (sign up)
A ZAI_API_KEY from Z.ai

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="z-ai-tracing-example"
export ZAI_API_KEY="<your-zai-api-key>"

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 Z.ai.")

Run Z.ai

# 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://api.z.ai/api/paas/v4/",
    api_key=os.environ["ZAI_API_KEY"],
)

response = client.chat.completions.create(
    model="glm-5.3",
    messages=[
        {
            "role": "user",
            "content": "What production signal should an LLM observability tool capture?",
        },
    ],
)

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

Expected output

Arize AX tracing initialized for Z.ai.
An LLM observability tool should capture prompt and response content, latency, token usage, model metadata, errors, and user feedback when available.

Verify in Arize

Open your Arize AX space and select project z-ai-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.
Z.ai spans missing but other spans present. OpenAIInstrumentor().instrument(...) must run before any import openai.
401 from Z.ai. Use your Z.ai API key, not your OpenAI or Arize API key.
Model not found. Replace glm-5.3 with a model available in your Z.ai account. Some Z.ai plans use a different OpenAI-compatible base URL, so confirm the endpoint in your Z.ai console.

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Evaluation

Prerequisites

Launch Arize

Install

Configure credentials

Setup tracing

Run Z.ai

Expected output

Verify in Arize

Check from the skill, CLI, or SDK

Troubleshooting

Resources

Z.ai OpenAI SDK Guide

OpenInference OpenAI Instrumentor

LLM Evaluation Guide

Agent Evaluation Guide

​Prerequisites

​Launch Arize

​Install

​Configure credentials

​Setup tracing

​Run Z.ai

​Expected output

​Verify in Arize

​Check from the skill, CLI, or SDK

​Troubleshooting

​Resources

Z.ai OpenAI SDK Guide

OpenInference OpenAI Instrumentor

LLM Evaluation Guide

Agent Evaluation Guide

Prerequisites

Launch Arize

Install

Configure credentials

Setup tracing

Run Z.ai

Expected output

Verify in Arize

Check from the skill, CLI, or SDK

Troubleshooting

Resources