How to beginner · 3 min read

How to call DeepSeek with LiteLLM

Q: How to call DeepSeek with LiteLLM

Use the openai Python SDK configured with DeepSeek's API endpoint and your API key, then call client.chat.completions.create with the deepseek-chat model. LiteLLM can invoke this by setting the base_url to DeepSeek's API and using the standard OpenAI-compatible interface.

Quick answer

Use the openai Python SDK configured with DeepSeek's API endpoint and your API key, then call client.chat.completions.create with the deepseek-chat model. LiteLLM can invoke this by setting the base_url to DeepSeek's API and using the standard OpenAI-compatible interface.

PREREQUISITES

Python 3.8+
DeepSeek API key
pip install openai>=1.0

Setup

Install the openai Python package (compatible with LiteLLM usage) and set your DeepSeek API key as an environment variable.

Run pip install openai to install the SDK.
Export your API key in your shell: export DEEPSEEK_API_KEY='your_api_key_here'.

bash

pip install openai

Step by step

Use the OpenAI-compatible SDK to call DeepSeek by specifying the base_url parameter pointing to DeepSeek's API endpoint. This example sends a chat completion request to the deepseek-chat model.

python

import os
from openai import OpenAI

# Initialize client with DeepSeek API key and base URL
client = OpenAI(
    api_key=os.environ["DEEPSEEK_API_KEY"],
    base_url="https://api.deepseek.com"
)

# Prepare messages for chat completion
messages = [
    {"role": "user", "content": "Hello, how can I use DeepSeek with LiteLLM?"}
]

# Call DeepSeek chat completion endpoint
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=messages
)

# Extract and print the response text
print(response.choices[0].message.content)

output

Hello! You can integrate DeepSeek with LiteLLM by configuring the OpenAI-compatible client to use DeepSeek's API endpoint and model, then sending chat completion requests as usual.

Common variations

You can switch models to deepseek-reasoner for reasoning tasks or adjust parameters like max_tokens and temperature. For asynchronous calls, use Python's asyncio with the OpenAI SDK's async methods. LiteLLM can proxy requests by setting base_url accordingly.

python

import asyncio
from openai import OpenAI

async def async_call():
    client = OpenAI(
        api_key=os.environ["DEEPSEEK_API_KEY"],
        base_url="https://api.deepseek.com"
    )
    response = await client.chat.completions.acreate(
        model="deepseek-chat",
        messages=[{"role": "user", "content": "Async call example."}]
    )
    print(response.choices[0].message.content)

asyncio.run(async_call())

output

This is an example of an asynchronous call to DeepSeek's chat model using the OpenAI SDK.

Troubleshooting

If you get authentication errors, verify your DEEPSEEK_API_KEY environment variable is set correctly.
For connection issues, ensure your network allows HTTPS requests to https://api.deepseek.com.
If the model name is invalid, confirm you are using deepseek-chat or deepseek-reasoner.

✅

Key Takeaways

Use the OpenAI SDK with the DeepSeek base_url to call DeepSeek models seamlessly.
Set your DeepSeek API key in the environment variable DEEPSEEK_API_KEY for authentication.
LiteLLM can integrate by configuring the OpenAI client with DeepSeek's endpoint and models.
Async calls and model parameter tuning are supported via the standard OpenAI SDK interface.
Check model names and network connectivity if you encounter errors.

Verified 2026-04 · deepseek-chat, deepseek-reasoner

Verify ↗