npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

n8n-nodes-deepseek-v4-thinking-fix

v0.2.1

Published

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control

Readme

n8n-nodes-deepseek-v4

Nó comunitário do n8n para os modelos DeepSeek V4 (deepseek-v4-flash e deepseek-v4-pro), com controle completo do Thinking Mode.

Modelos suportados

| Model ID | Alias legado | Thinking | |---|---|---| | deepseek-v4-flash | deepseek-chat | Opcional | | deepseek-v4-pro | deepseek-reasoner | Opcional | | deepseek-chat | — | Sem thinking por padrão | | deepseek-reasoner | — | Com thinking por padrão |

Features

  • Thinking Mode toggle — Desabilite, habilite com high ou max effort
  • ✅ Retorna reasoning_content separado do content (opcional)
  • ✅ Parâmetros temperature, top_p, presence_penalty, frequency_penalty são automaticamente omitidos quando thinking está ativo (evita conflito com a API)
  • ✅ Suporte a JSON Output Mode (response_format: json_object)
  • ✅ Stop sequences configuráveis
  • ✅ Custom Base URL (útil para proxies OpenAI-compatible)

Instalação

Via npm (produção)

npm install n8n-nodes-deepseek-v4

Via n8n UI

Vá em Settings → Community Nodes → Install e busque n8n-nodes-deepseek-v4.

Desenvolvimento local

cd n8n-nodes-deepseek-v4
npm install
npm run build
# Copie a pasta para ~/.n8n/custom/ ou use npm link

Configuração da Credencial

  1. Acesse platform.deepseek.com e gere uma API Key
  2. No n8n, vá em Credentials → New → DeepSeek API
  3. Insira a API Key e salve

Parâmetros do Nó

| Parâmetro | Descrição | |---|---| | Model | Modelo a usar (v4-flash, v4-pro, etc.) | | System Message | Prompt de sistema (opcional) | | User Message | Prompt do usuário | | Thinking Mode | Disabled / Enabled – High / Enabled – Max | | Return Thinking Content | Incluir reasoning_content no output | | Temperature | Temperatura (ignorada com thinking ativo) | | Max Tokens | Máximo de tokens gerados | | JSON Output Mode | Força output como JSON válido | | Stop Sequences | Sequências de parada (vírgula separadas) |

Saída

{
  "content": "Resposta final do modelo",
  "reasoning_content": "Chain-of-thought (apenas se thinking ativo e Return habilitado)",
  "model": "deepseek-v4-flash",
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 200,
    "total_tokens": 300
  },
  "finish_reason": "stop"
}

Por que desabilitar o Thinking?

O Thinking Mode consome mais tokens e é mais lento. Para tarefas simples (classificação, extração, tradução, geração de texto direto), desabilitá-lo é mais eficiente e barato. O nó envia explicitamente {"thinking": {"type": "disabled"}} para garantir que o modelo não use reasoning mesmo quando o default da API for enabled.

Licença

MIT