---
title: Chat DeepSeek
description: Use DeepSeek chat and reasoning models.
---

Give an AI node access to DeepSeek's chat and reasoning models, using your own DeepSeek API key.

Pick a saved connection in the **Authentication** field, or create one from there.

## What it does

Chat DeepSeek is a model you plug into the **Model** slot of an AI node, such as the [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/) or [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/). It does not run on its own and has no output. When the AI node runs, it sends its messages to DeepSeek with your key and gets the reply back.

* **Temperature** is 0 when you leave it empty, so answers are focused and repeatable.
* Replies are capped at **Max Tokens** (4096 by default).
* A failed request is retried up to **Max Retries** times (2 by default). A request that gets no answer within 60 seconds fails.

## When to use it

* Everyday text jobs at a low price per token: use `deepseek-chat`.
* Problems that need step-by-step thinking, such as maths or logic: use `deepseek-reasoner`.
* You want an alternative to OpenAI or Anthropic with your own DeepSeek account.

## Inputs and settings

Type the **Model** id as DeepSeek names it: `deepseek-chat` or `deepseek-reasoner`. A reasoning model takes longer to answer and uses more tokens, so raise **Max Tokens** if its answers get cut off.

## Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

* **Model** slot of [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/), [Q\&A Agent](/nodes/builtin/ai/aiagents/qanode/), [RAG Agent](/nodes/builtin/ai/aiagents/ragnode/), [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/), [Indexer](/nodes/builtin/ai/aiagents/indexernode/), [Text Classifier](/nodes/builtin/ai/aiagents/textclassifiernode/), [Sentiment Analysis](/nodes/builtin/ai/aiagents/sentimentanalysisnode/), [Summarization](/nodes/builtin/ai/aiagents/summarizationchainnode/), [Information Extractor](/nodes/builtin/ai/aiagents/informationextractornode/), [Guardrails](/nodes/builtin/ai/aiagents/guardrails/), [Auto-fixing Output Parser](/nodes/builtin/ai/aidependencies/outputparser/autofixingoutputparser/)

The AI node you connect it to produces the output. Chat DeepSeek only decides which model answers.

## Dependencies and credentials

* **Authentication** (connection): required. See [Connect DeepSeek](/app/connections/deepseek/).

In **Authentication**, use a Bearer Token credential that holds your DeepSeek API key. Create the key on the API keys page of the DeepSeek platform. See [Create a credential](/app/connections/create/).

## Example workflow

1. A [Context Menu](/nodes/builtin/trigger/contextmenu/) trigger on selected text.
2. [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/) with **Prompt** `Check this calculation step by step and give the correct result: {{ $input.selectionText }}`.
3. Chat DeepSeek in its **Model** slot, **Model** `deepseek-reasoner`, **Max Tokens** `8000`.
4. [Clipboard Write](/nodes/extension/clipboardwrite/) with **Text** `{{ $input.response }}`.

## Common issues

* **"Model parameter is required and cannot be empty".** Fill in **Model**.
* **A 401 error.** The key is wrong or revoked. Create a new key and update the credential.
* **A 402 or "insufficient balance" error.** Top up your DeepSeek account.
* **The request times out.** A reasoning model can think for a long time. Try `deepseek-chat`, or a shorter prompt.

## Related nodes

* [Basic LLM Chain](/nodes/builtin/ai/aiagents/basicllmchainnode/): send one prompt and get a reply.
* [Tools Agent](/nodes/builtin/ai/aiagents/toolsagentnode/): an agent that can use tools and memory.
* [Chat OpenRouter](/nodes/builtin/ai/aidependencies/llm/openrouter/): DeepSeek and many other models with one key.