--- title: How to Use DeepSeek R1 in VSCode for free | daily.dev description: DeepSeek R1 is a powerful, open-source AI model that excels in logic, mathematics, and code generation. It's free and can be integrated into Visual Studio Code... canonical: https://daily.dev/posts/how-to-use-deepseek-r1-in-vscode-for-free-q1qckui1t twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How to Use DeepSeek R1 in VSCode for free | daily.dev og:description: DeepSeek R1 is a powerful, open-source AI model that excels in logic, mathematics, and code generation. It's free and can be integrated into Visual Studio Code... og:url: https://daily.dev/posts/how-to-use-deepseek-r1-in-vscode-for-free-q1qckui1t og:image: https://api.daily.dev/og/posts/Q1QcKui1t.png og:image:alt: How to Use DeepSeek R1 in VSCode for free og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How to Use DeepSeek R1 in VSCode for free **[OpenSouls](https://daily.dev/sources/opensouls)** · [@anmolbaranwal](https://daily.dev/anmolbaranwal) · 1175 upvotes · 46 comments ## Summary DeepSeek R1 is a powerful, open-source AI model that excels in logic, mathematics, and code generation. It's free and can be integrated into Visual Studio Code using tools like LM Studio, Ollama, and Jan. Choose from models ranging from 1.5B to 70B parameters depending on your hardware. Running it locally is recommended for privacy and to avoid costs associated with API usage. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@mrgraphene** · 50 upvotes > I guess you are deliberately withholding information since the R1 you are talking about are the distilled versions, which are not as intelligent as the true R1 on deepseeks chat, and over their api. If you are using the chat its free like facebook is free, in other words they are gathering information about you and your prompts. **@qwertydiy** · 13 upvotes > We are officially in an era where large non developer applications are open source (at least in AI) and we are yet again seeing "Open"AI collapse slowly. Hopefully other companies take notice but first I would enjoy this historic moment. **@simonebogni92** · 8 upvotes > I fail to understand how someone would trust a product that has its base of operations and data servers in China and that does not comply with the most important privacy regulations... **@joeclaxton** · 3 upvotes > This is a good 'how to' article. However, I've used chatgpt since it started and while Deepseek is good, I don't think its that good. It reminds me of the early days of chatgpt. Also it gets curt and stand offish if you try to get it to be creative and think out side the box. if you're looking for a choice of LLM I would visit the Ollama website directly and choose. As the article indicates you'll also need a beefy spec PC to run it. As a Linux user, for accessing Ai alongside my coding I use the warp Ai terminal. Its integrated Ai with your coding from the get go and no hassle to install or... **@gerryhaus** · 3 upvotes > I like Jan.ai for running AI locally, but they say their API is OpenAI compliant, which I am not so sure if that's true. I can get DeepSeek working with OpenAI's C# wrapper (quite easy), but not Jan.ai > > Nevermind, this test works now > > oops = new OpenAIClientOptions(); > oops.Endpoint = new Uri("http://127.0.0.1:1337/v1"); > ApiKeyCredential janai = new ApiKeyCredential("nokey4u"); > client = new ChatClient(model: "tinyllama-1.1b", janai, oops); > > I don't have r1 downloaded yet... ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments - [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments - [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#devtools](https://daily.dev/tags/devtools), [#machine-learning](https://daily.dev/tags/machine-learning), [#open-source](https://daily.dev/tags/open-source), [#vscode](https://daily.dev/tags/vscode) [View this post on daily.dev](https://daily.dev/posts/how-to-use-deepseek-r1-in-vscode-for-free-q1qckui1t) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/how-to-use-deepseek-r1-in-vscode-for-free-q1qckui1t","headline":"How to Use DeepSeek R1 in VSCode for free","text":"Shared: How to Use DeepSeek R1 for Free in Visual Studio Code with Cline or Roo Code","url":"https://daily.dev/posts/how-to-use-deepseek-r1-in-vscode-for-free-q1qckui1t","datePublished":"2025-01-27T08:54:01.912Z","dateModified":"2026-03-15T07:56:43.056Z","author":{"@type":"Person","name":"Anmol Baranwal","url":"https://daily.dev/anmolbaranwal","image":"https://avatars.githubusercontent.com/u/74038190?v=4","description":"Just a tech guy who loves writing and building cool stuff","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":19790}},"image":"https://media.daily.dev/image/upload/s--VDukGCjf--/f_auto/v1722860399/public/Placeholder%2002","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1175},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":46}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/SOwyQBtCR"},"comment":[{"@type":"Comment","text":"I guess you are deliberately withholding information since the R1 you are talking about are the distilled versions, which are not as intelligent as the true R1 on deepseeks chat, and over their api. If you are using the chat its free like facebook is free, in other words they are gathering information about you and your prompts.","datePublished":"2025-01-28T08:12:08.184Z","url":"https://daily.dev/posts/Q1QcKui1t#c-XXZMY58mQ","author":{"@type":"Person","name":"Graphene","url":"https://daily.dev/mrgraphene","image":"https://avatars.githubusercontent.com/u/122998224?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":50}},{"@type":"Comment","text":"We are officially in an era where large non developer applications are open source (at least in AI) and we are yet again seeing "Open"AI collapse slowly. Hopefully other companies take notice but first I would enjoy this historic moment.","datePublished":"2025-01-29T07:53:42.608Z","url":"https://daily.dev/posts/Q1QcKui1t#c-WazfjIuoP","author":{"@type":"Person","name":"Rene Yibowei","url":"https://daily.dev/qwertydiy","image":"https://media.daily.dev/image/upload/s--QlvtioAW--/f_auto/v1746524446/avatars/avatar_aTUl3chxFyPngKtboGisL"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":13}},{"@type":"Comment","text":"I fail to understand how someone would trust a product that has its base of operations and data servers in China and that does not comply with the most important privacy regulations…","datePublished":"2025-01-30T17:25:19.990Z","url":"https://daily.dev/posts/Q1QcKui1t#c-bBYTvpalI","author":{"@type":"Person","name":"Simone Bogni","url":"https://daily.dev/simonebogni92","image":"https://media.daily.dev/image/upload/s--dcNhpNF9--/f_auto,q_auto/v1694500941/avatars/avatar_lc2D0L4tmUDxI4L5LCwIp"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":8}},{"@type":"Comment","text":"This is a good ‘how to’ article. However, I’ve used chatgpt since it started and while Deepseek is good, I don’t think its that good. It reminds me of the early days of chatgpt. Also it gets curt and stand offish if you try to get it to be creative and think out side the box. if you’re looking for a choice of LLM I would visit the Ollama website directly and choose. As the article indicates you’ll also need a beefy spec PC to run it. As a Linux user, for accessing Ai alongside my coding I use the warp Ai terminal. Its integrated Ai with your coding from the get go and no hassle to install or drain on your resources to use. see https://www.warp.dev/warp-ai","datePublished":"2025-01-31T10:15:00.274Z","dateModified":"2025-01-31T10:18:06.822Z","url":"https://daily.dev/posts/Q1QcKui1t#c-9nxZyMs0e","author":{"@type":"Person","name":"Joe Claxton","url":"https://daily.dev/joeclaxton","image":"https://lh3.googleusercontent.com/a/ACg8ocIZHOv5fE4IMdc5BAwRppBUQQB8nYKxWjIXY2jfIWPg92QiaXFaoQ=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"I like Jan.ai for running AI locally, but they say their API is OpenAI compliant, which I am not so sure if that’s true. I can get DeepSeek working with OpenAI’s C# wrapper (quite easy), but not Jan.ai\nNevermind, this test works now\noops = new OpenAIClientOptions();\noops.Endpoint = new Uri(“http://127.0.0.1:1337/v1”);\nApiKeyCredential janai = new ApiKeyCredential(“nokey4u”);\nclient = new ChatClient(model: “tinyllama-1.1b”, janai, oops);\nI don’t have r1 downloaded yet…","datePublished":"2025-01-30T02:08:48.335Z","dateModified":"2025-01-30T02:35:00.024Z","url":"https://daily.dev/posts/Q1QcKui1t#c-o1wEIjYAD","author":{"@type":"Person","name":"Gerry","url":"https://daily.dev/gerryhaus","image":"https://media.daily.dev/image/upload/s--Zq08ufWD--/f_auto/v1745783913/avatars/avatar_xLIbosP0lNB6caVBOBujb"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/opensouls","name":"OpenSouls"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"OpenSouls","item":"https://daily.dev/squads/opensouls"},{"@type":"ListItem","position":3,"name":"How to Use DeepSeek R1 in VSCode for free"}]} ```