How to beginner · 3 min read

How to run DeepSeek with Ollama

Q: How to run DeepSeek with Ollama

You cannot run DeepSeek models directly with Ollama because Ollama runs local models without API keys, while DeepSeek is a cloud API accessed via the OpenAI-compatible SDK. Use the openai Python SDK with DeepSeek by setting the base_url to https://api.deepseek.com and your API key from os.environ.

Quick answer

You cannot run DeepSeek models directly with Ollama because Ollama runs local models without API keys, while DeepSeek is a cloud API accessed via the OpenAI-compatible SDK. Use the openai Python SDK with DeepSeek by setting the base_url to https://api.deepseek.com and your API key from os.environ.

PREREQUISITES

Python 3.8+
DeepSeek API key (set in environment variable DEEPSEEK_API_KEY)
pip install openai>=1.0

Setup

Install the openai Python SDK (v1 or later) to access DeepSeek's API. Set your DeepSeek API key in the environment variable DEEPSEEK_API_KEY. Ollama runs local models and does not support remote API calls, so you use the OpenAI-compatible client with DeepSeek's base_url.

bash

pip install openai>=1.0

Step by step

Use the openai SDK with base_url set to DeepSeek's API endpoint. This example sends a chat completion request to the deepseek-chat model.

python

import os
from openai import OpenAI

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

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello from DeepSeek via Ollama?"}]
)

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

output

Hello from DeepSeek via Ollama? I'm here to assist you!

Common variations

You can switch models to deepseek-reasoner for reasoning tasks or adjust max_tokens and temperature parameters. Ollama itself does not support remote API calls, so you cannot run DeepSeek models inside Ollama directly. Instead, run Ollama locally for local models and use the OpenAI-compatible client for DeepSeek cloud models.

python

response = client.chat.completions.create(
    model="deepseek-reasoner",
    messages=[{"role": "user", "content": "Explain quantum computing in simple terms."}],
    max_tokens=500,
    temperature=0.7
)
print(response.choices[0].message.content)

output

Quantum computing uses quantum bits that can be in multiple states simultaneously, enabling faster problem solving for certain tasks.

Troubleshooting

If you get authentication errors, verify your DEEPSEEK_API_KEY environment variable is set correctly.
If requests time out, check your network connection and DeepSeek service status.
Remember Ollama runs local models only; it cannot proxy or run DeepSeek cloud models.

✅

Key Takeaways

Use the OpenAI-compatible openai SDK with base_url="https://api.deepseek.com" to access DeepSeek models.
Ollama runs local models only and cannot run or proxy DeepSeek cloud models.
Set your DeepSeek API key in os.environ["DEEPSEEK_API_KEY"] before running code.
Switch between deepseek-chat and deepseek-reasoner models for general chat or reasoning tasks.
Troubleshoot authentication and network issues by verifying environment variables and connectivity.

Verified 2026-04 · deepseek-chat, deepseek-reasoner, gpt-4o, llama3.2

Verify ↗