Skip to main content
DeepSeek offers competitive pricing relative to the quality of its models. DeepSeek R1 is a reasoning model that thinks through problems before producing output, which can improve translation accuracy on complex graphs.

​
Getting an API key

1

Create a DeepSeek account

Go to platform.deepseek.com and sign in or create an account.
2

Generate an API key

Navigate to API keys and create a new key. Copy it before closing.
3

Add the key in Unreal Engine

Open Edit → Project Settings → Plugins → Node to Code → LLM Services → DeepSeek and paste your key into the API Key field.
4

Select DeepSeek as your provider

Under Node to Code | LLM Provider, set Provider to DeepSeek.

​
Model selection

Set the model under Node to Code | LLM Services | DeepSeek → DeepSeek Model.
Display nameModel IDNotes
DeepSeek R1deepseek-reasonerDefault — recommended
DeepSeek V3deepseek-chatChat/instruction model
DeepSeek R1 (deepseek-reasoner) is a reasoning model — it performs an internal chain-of-thought before responding. This generally produces more accurate translations, especially for complex Blueprint logic.DeepSeek V3 (deepseek-chat) is a standard chat/instruction model. It responds faster and costs less per request, but may produce less thorough translations on intricate graphs.

Build docs developers (and LLMs) love

Get started for freeTalk to us