DeepSeek

Consume DeepSeek AI

Actions2

Chat Actions
- Complete
FIM Actions
- Complete

Overview

The DeepSeek node for n8n enables you to interact with the DeepSeek AI platform, specifically leveraging its Chat resource to generate conversational completions. This is useful for scenarios where you want to automate text generation, build chatbots, summarize content, or create interactive assistants within your workflows. For example, you could use this node to answer customer queries, provide automated support, or generate creative writing prompts.

Properties

Below are the supported input properties for the Chat → Complete operation:

Display Name	Type	Description
Model	options	The model which will generate the completion. Learn more. Models are dynamically loaded from DeepSeek and filtered to those starting with `deepseek-`.
Prompt	fixedCollection	A collection of messages forming the conversation history. Each message includes a Role (Assistant, System, User) and Content (the actual text).
Simplify	boolean	Whether to return a simplified version of the response instead of the raw data. If enabled, only the main choices array is returned.
Options	collection	Additional fine-tuning parameters:
	Frequency Penalty	number
	Maximum Number of Tokens	number
	Presence Penalty	number
	Sampling Temperature	number
	Top P	number
	Response Format	json
	Logprobs	boolean
	Top Logprobs	number

Output

json:
- By default, the node outputs the full response from DeepSeek's API, which typically includes fields such as choices, usage, and other metadata.
- If Simplify is enabled, the output is reduced to just the choices array, which contains the generated completions/messages.
- Example simplified output:
```
[
  {
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop",
    "index": 0
  }
]
```
Binary Data:
- This node does not output binary data.

Dependencies

External Service: Requires access to the DeepSeek API.
API Key: You must configure DeepSeek API credentials (deepSeekApi) in n8n.
Environment: No special environment variables required beyond standard n8n credential setup.

Troubleshooting

Invalid API Key / Authentication Error:
Ensure your DeepSeek API credentials are correctly configured in n8n.
Model Not Found:
If you select a model that is not available or incorrectly filtered, ensure the model list is refreshed and matches the expected prefix (deepseek-).
Token Limit Exceeded:
If you request more tokens than allowed by the selected model, reduce the "Maximum Number of Tokens" value.
Missing Required Fields:
Make sure all required fields (such as Model and at least one Prompt message) are provided.
Logprobs/Top Logprobs Misconfiguration:
If you set "Top Logprobs" without enabling "Logprobs", the API may return an error. Always enable "Logprobs" when using "Top Logprobs".