> For the complete documentation index, see [llms.txt](https://docs.gpmautomate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.gpmautomate.com/automate-en/action-guides/ai/deep-seek.md). # DeepSeek DeepSeek is a built-in action that allows your GPM Automate script to connect directly to the DeepSeek API system. With its outstanding advantage of ultra-low cost and logical thinking capabilities, programming, and a very powerful language, this action is a perfect alternative or complement alongside Chat GPT for automating content creation tasks, data analysis, or intelligent text processing. #### Instructions for registering, purchasing API, and configuring the DeepSeek action The mechanism of operation and cost calculation through the DeepSeek API is similar to OpenAI (Prepaid, use as much as you need). The specific setup process includes the following steps: **Step 1: Register an account and Top up (API Credits)** 1. You visit the official API management page of DeepSeek at: [https://platform.deepseek.com](https://platform.google.com/url?q=https://platform.deepseek.com) and proceed to create an account. 2. After logging in, go to the Top up or Billing section to link an international payment card (Visa/Mastercard) and top up the desired amount (usually a minimum of $2 - $5) to activate the API usage quota. **Step 2: Initialize and obtain the DeepSeek API Key** 1. In the left menu bar, select the API Keys section. 2. Click on the Create new secret key button, name the key (e.g., `GPM_DeepSeek_Key`). 3. The system will display a long security string starting with `sk-...`. You should Copy and save it immediately as this string will be hidden and will not be displayed again. **Step 3: Obtain the exact Model names** DeepSeek provides two extremely optimized core models; you just need to enter one of the following identifiers accurately in the configuration box of GPM. You can view the list of DeepSeek models here: . #### Configuration parameters in GPM Automate: When dragging the DeepSeek action into the Main workflow, you set it up as follows: * API Key: Paste the secret key `sk-...` obtained in Step 2 here (or pass it through a variable for security). * DeepSeek Model: Enter the exact string `deepseek-chat` or `deepseek-reasoning`. * Prompt: Enter the content of your command or detailed request (e.g., `"Please analyze the following conversation and extract the customer's phone number: $webContent"`). * Output variable: Name the output variable (e.g., `deepseekResult`) so that the system automatically saves the AI's response text string, ready for subsequent data entry actions. #### Practical example: Automatically translating and rewriting article titles (Rewrite Title) to avoid copyright When you do Marketing, POD, or create content in international markets (such as the German market), you need to scrape product titles from E-commerce sites in English, then translate them into German and rewrite them a bit to post on your store to optimize SEO and avoid content duplication. * Configuration method: * Suppose you have scraped the original English title and saved it in the variable `$originTitle`. * Call the DeepSeek action in the script. * API Key: `sk-proj-xxxxxxxxxxxxxxxxxxxx` * DeepSeek Model: `deepseek-v4-flash` * Prompt: You enter the directive content for the AI: ``` Please translate the following product title into German and rewrite it to be as natural, concise, and appealing for marketing as possible. Original title: "$originTitle". Only return the result string after translation and rewriting, without adding any leading or explanatory text. ``` * Output variable: Name the output variable `aiContent`. Result: The system will push the title in the variable `$originTitle` to DeepSeek for processing. The AI will quickly translate and optimize the wording into German, then directly load the most concise text result into the variable `$aiContent`. In the next steps, you just need to call this `$aiContent` variable to automatically fill in the input field on your website, helping to automate the cross-border content creation process very professionally.
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.gpmautomate.com/automate-en/action-guides/ai/deep-seek.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.