# Can we create a GPT on top of the Deepseek api? **URL:** \ **Category:** Questions\ **Created:** [January 4, 2025, 9:07pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343 "2025-01-04T21:07:26Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 4, 2025, 9:07pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/1 "2025-01-04T21:07:26Z")
Can we now, or will we be able to, use the Deepseek api? The model is reviewed as very capable, and inexpensive. Thanks. ---
**Author:** ![admin\_mike](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/admin_mike/32/283_2.png) [@admin\_mike](https://community.pickaxe.co/u/admin_mike)\ **Post date:** [January 7, 2025, 12:08am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/2 "2025-01-07T00:08:04Z")
Currently we do provide the famed Chinese AI model [DeepSeek](https://www.deepseek.com/) on our platform. We also provide models from OpenAI, Anthropic, and the French LLM provider Mistral. We also recently added an open-source LLama model from Meta which is, shall we say, very _open-minded_. To create a chatbot or GPT on top of the DeepSeek model simply go to [our chatbot builder](https://beta.pickaxeproject.com/builder/templates/chat) and select Deepseek from the dropdown menu. It is free and available to all users on the platform. Though a warning: due its popularity, the API is somewhat unstable. You may experience some instability while the we stabilize the model. ![Screenshot 2025-02-10 at 4.47.14 PM](https://canada1.discourse-cdn.com/flex004/uploads/pickaxeproject/original/2X/b/bbdd36cb76644d0ffc225d4c8f75f99088d7938e.png) ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 7, 2025, 12:22am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/3 "2025-01-07T00:22:16Z")
Thanks, Mike. The main reason I’m interested in DeepSeek is that it is astonishingly inexpensive and powerful. I’ll poke into adding it via an Action. John ---
**Author:** ![ihmunro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ihmunro/32/592_2.png) [@ihmunro](https://community.pickaxe.co/u/ihmunro)\ **Post date:** [January 7, 2025, 1:45am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/4 "2025-01-07T01:45:13Z")
You can run a make action calling a webhook that then can run an Openrouter module with Deepseek. Regards ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 7, 2025, 2:01am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/5 "2025-01-07T02:01:58Z")
Great to know, ihmunro! Thanks for taking the time to reply. John ---
**Author:** ![editman](https://avatars.discourse-cdn.com/v4/letter/e/ba8739/32.png) [@editman](https://community.pickaxe.co/u/editman)\ **Post date:** [January 11, 2025, 2:39pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/6 "2025-01-11T14:39:35Z")
would really appreciate if you share any code or action you make. I’d also love to use DeepSeek instead of Sonnet haha ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 11, 2025, 5:31pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/7 "2025-01-11T17:31:04Z")
Will do, although with o3 mini coming out soon, we may have a really capable inexpensive OpenAI model to use (assuming Pickaxe will support that) ---
**Author:** ![ihmunro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ihmunro/32/592_2.png) [@ihmunro](https://community.pickaxe.co/u/ihmunro)\ **Post date:** [January 11, 2025, 6:21pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/8 "2025-01-11T18:21:19Z")
Just create an action to a [Make.com](http://Make.com) scenario where you can call out Open Router with Deepseek ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 11, 2025, 7:02pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/9 "2025-01-11T19:02:59Z")
That’s a great idea. Have you been using Deepseek via OpenRouter? ---
**Author:** ![ihmunro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ihmunro/32/592_2.png) [@ihmunro](https://community.pickaxe.co/u/ihmunro)\ **Post date:** [January 11, 2025, 7:18pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/10 "2025-01-11T19:18:59Z")
Yes - I am now swapping out my chatgpt modules with openrouter ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 11, 2025, 7:30pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/11 "2025-01-11T19:30:19Z")
If you’re up for it, please share your code etc. ---
**Author:** ![zerodot](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/zerodot/32/542_2.png) [@zerodot](https://community.pickaxe.co/u/zerodot)\ **Post date:** [January 12, 2025, 7:33am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/12 "2025-01-12T07:33:34Z")
Wow! Gemini sounds fantastic! We are using it a lot internally due to its context window length. It would be a great addition! ---
**Author:** ![Ned.Malki](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ned.malki/32/5918_2.png) [@Ned.Malki](https://community.pickaxe.co/u/Ned.Malki)\ **Post date:** [January 12, 2025, 12:35pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/13 "2025-01-12T12:35:09Z")
Nice! ![](https://canada1.discourse-cdn.com/flex004/uploads/pickaxeproject/original/2X/5/51e12b774f907183369a913f8924dad2f6819cc9.gif) ---
**Author:** ![Ned.Malki](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ned.malki/32/5918_2.png) [@Ned.Malki](https://community.pickaxe.co/u/Ned.Malki)\ **Post date:** [January 12, 2025, 12:37pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/14 "2025-01-12T12:37:25Z")
Agreed! I tried out [aistudio.google.com](http://aistudio.google.com) recently and was blown away by how far they have come. They’re serious competitors right now ---
**Author:** ![admin\_mike](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/admin_mike/32/283_2.png) [@admin\_mike](https://community.pickaxe.co/u/admin_mike)\ **Post date:** [January 13, 2025, 4:12pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/15 "2025-01-13T16:12:03Z")
Google is really catching up. Google moves more slowly than the other AI companies due to their size but we’re starting to see the dividends from their DeepMind lab, large dataset (search + youtube) and giant GPU hoard. We will need to integrate Gemini into the platform sooner rather than later! ---
**Author:** ![zerodot](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/zerodot/32/542_2.png) [@zerodot](https://community.pickaxe.co/u/zerodot)\ **Post date:** [January 17, 2025, 2:34pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/16 "2025-01-17T14:34:58Z")
A request. The real utility of gemini lies in its context window and multimodality. Even if its integrated, if the file uploads are not fed into the context window of gemini (and sent to a vector db instead), the utility would be lost. Similarly, if one cant send it audio/video files, it pretty much becomes a gpt-4o-mini. Atleast, for the user uploaded files (not the knowledge base files), could there be a way to send audio/video and text/pdf files directly to gemini alongwith the prompt and so one can benefit from Gemini’s context window and multimodal functions? ---
**Author:** ![admin\_mike](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/admin_mike/32/283_2.png) [@admin\_mike](https://community.pickaxe.co/u/admin_mike)\ **Post date:** [January 17, 2025, 7:41pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/17 "2025-01-17T19:41:49Z")
Yes there is actually a way to do this @zerodot. Let me explain. The [way end-user uploads functions](https://community.pickaxe.co/t/user-document-uploads-rag-vs-deep-learning-token-consumption/3383/2) actually allows this. Here’s a rundown: - The end-user upload process always looks the **maximum input length** setting of a Pickaxe. This can be 1000 tokens or 100,000 tokens. - Then it looks at the size of the document. This could be 1000 tokens, 30,000 tokens, or 3,000,000 tokens. - If the document fits into the maximum input length, then the system dumps the entire document contents into the context conversation. No vector embeddings. If it does not fit, it’s turned into vector embeddings. The takeaway for Pickaxe users is you can select which process you prefer based on your use case by _increasing the the size of the maximum input length._ ---
**Author:** ![zerodot](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/zerodot/32/542_2.png) [@zerodot](https://community.pickaxe.co/u/zerodot)\ **Post date:** [January 18, 2025, 4:33am UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/18 "2025-01-18T04:33:15Z")
Oh Great! Didnt realize that. Thank you! ---
**Author:** ![christiaan](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/christiaan/32/231_2.png) [@christiaan](https://community.pickaxe.co/u/christiaan)\ **Post date:** [January 21, 2025, 12:27pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/19 "2025-01-21T12:27:19Z")
Deepseek outclass ChatGPT 4.o for content. Will do the job manually until there is another solution. Test it yourself! ---
**Author:** ![source](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/source/32/1722_2.png) [@source](https://community.pickaxe.co/u/source)\ **Post date:** [January 21, 2025, 2:12pm UTC](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343/20 "2025-01-21T14:12:19Z")
DeepSeek continues to amaze. I really do hope that the pickax developers will look closely at it and make it accessible to Us soon. [Next page](https://community.pickaxe.co/t/can-we-create-a-gpt-on-top-of-the-deepseek-api/3343.md?page=2)