DeepSeek Tracing

DeepSeek provides reasoning and chat models through an API format compatible with OpenAI. Set the OpenAI client’s base_url to https://api.deepseek.com and Phoenix captures each call through openinference-instrumentation-openai.

This page instruments your application’s OpenAI SDK calls to DeepSeek. It does not require a separate DeepSeek-specific OpenInference instrumentor.

Install

pip install arize-phoenix-otel openinference-instrumentation-openai openai

Setup

Add your DeepSeek API key from the DeepSeek platform, along with your Phoenix connection details, as environment variables:

export DEEPSEEK_API_KEY="<your-deepseek-api-key>"
export PHOENIX_COLLECTOR_ENDPOINT="<your-phoenix-collector-endpoint>"  # use http://localhost:6006 for local Phoenix
export PHOENIX_API_KEY="<your-phoenix-api-key>"  # required for Phoenix Cloud or authenticated Phoenix

Connect your application to Phoenix with the register function:

Run DeepSeek

import os
import openai

client = openai.OpenAI(
    base_url="https://api.deepseek.com",
    api_key=os.environ["DEEPSEEK_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[
        {
            "role": "user",
            "content": "Explain how tracing helps evaluate an AI agent.",
        },
    ],
)
print(response.choices[0].message.content)

Observe

Now that you have tracing set up, all invocations of the OpenAI client pointed at DeepSeek will be streamed to your running Phoenix for observability and evaluation. Each request appears as a ChatCompletion LLM span with the prompt, response, model name, token usage, and latency.

Common Issues

No traces in Phoenix: Confirm PHOENIX_COLLECTOR_ENDPOINT (and PHOENIX_API_KEY if your Phoenix requires one) is set in the same shell that runs your app
DeepSeek spans missing: Call register() before you create the OpenAI client, and make sure openinference-instrumentation-openai is installed so auto_instrument=True picks it up
401 from DeepSeek: Use your DeepSeek API key, not your OpenAI key
Model not found: Confirm the model name is available in your DeepSeek account and replace deepseek-v4-pro if needed
Base URL: Ensure you’re using https://api.deepseek.com as the base URL

Developer Tools

LLM Providers

TypeScript

Python

Java

.NET

Platform

Vector Databases

Sandboxes

Evaluation Integrations

Coding Agents

DeepSeek Tracing

Install

Setup

Run DeepSeek

Observe

Common Issues

Resources

DeepSeek API Documentation

OpenInference OpenAI Instrumentation

​Install

​Setup

​Run DeepSeek

​Observe

​Common Issues

​Resources

DeepSeek API Documentation

OpenInference OpenAI Instrumentation

Install

Setup

Run DeepSeek

Observe

Common Issues

Resources