DeepSeek has been making waves with R1— a powerful model that reasons like OpenAI’s GPT-4o while exposing its thought process. Now, you can easily use it in LangChain, alongside the faster DeepSeek-V3, in both Python and JS.

You can:

Run it locally with Ollama
Use DeepSeek's own API
Deploy on inference platforms like Together, Fireworks AI, and more

Whether you're building agentic workflows or reasoning-heavy apps, DeepSeek + LangChain makes it easy.

Python docs: https://python.langchain.com/docs/integrations/chat/deepseek/

JavaScript docs: https://js.langchain.com/docs/integrations/chat/deepseek/