# GPT-4o mini landed - going to be supported? **URL:** https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097 **Category:** Feature **Tags:** completed, ai **Created:** [July 18, 2024, 8:04pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097 "2024-07-18T20:04:39Z") **Posts on this page:** 8 **Page:** 1
### Author: ![MachineScholar](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/machinescholar/32/424719_2.png) [@MachineScholar](https://meta.discourse.org/u/MachineScholar) #### Post date: [July 18, 2024, 8:04pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/1 "2024-07-18T20:04:39Z")
Title says it all – just curious if there will be a plan to support this model and if so, is there a rough estimate on when it could be implemented? This is a massive improvement for anyone currently using GPT 3.5 Turbo as it’s smarter and over 60% cheaper. [More info about this model on TechCrunch](https://techcrunch.com/2024/07/18/openai-unveils-gpt-4o-mini-a-small-ai-model-powering-chatgpt/?guccounter=1&guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&guce_referrer_sig=AQAAAHp4_B2uiDyynLTYHr2CC8kYxII3TFK4k_6FpppAFgVLPDMEimc8zbre7wwBph8x9Qat0rSWTboMC5pYeYl_k0dhq6KQGWRjzUx9tG8GudqZD6GHDJ_2YDnCckrj8kBbHFNzl2AK_453XbA9nwm2N_Dtjd6Hgv0wGZBf8XLL-ylJ) ---
### Author: ![Aaron\_Walsh](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/aaron_walsh/32/312661_2.png) [@Aaron\_Walsh](https://meta.discourse.org/u/Aaron_Walsh) #### Post date: [July 18, 2024, 8:15pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/2 "2024-07-18T20:15:32Z")
[https://meta.discourse.org/t/discourse-chatbot/256652/899?u=aaron\_walsh](https://meta.discourse.org/t/discourse-chatbot/256652/899) ---
### Author: ![awesomerobot](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/awesomerobot/32/142900_2.png) [@awesomerobot](https://meta.discourse.org/u/awesomerobot) #### Post date: [July 18, 2024, 8:15pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/3 "2024-07-18T20:15:51Z")
It already works with the [Discourse AI plugin](https://meta.discourse.org/t/discourse-ai/259214), you just need to make sure to use `gpt-4o-mini` as the name in your LLM configuration: ![image](https://global.discourse-cdn.com/meta/original/4X/7/c/1/7c184aa7da5bfa663d2d8f31887d47e923b17219.png) ---
### Author: ![MachineScholar](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/machinescholar/32/424719_2.png) [@MachineScholar](https://meta.discourse.org/u/MachineScholar) #### Post date: [July 18, 2024, 8:19pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/4 "2024-07-18T20:19:41Z")
Well this is embarrassing. Thanks boss 😁🤖 Perhaps I haven’t played around with it enough - note made ---
### Author: ![Jagster](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/jagster/32/192154_2.png) [@Jagster](https://meta.discourse.org/u/Jagster) #### Post date: [July 18, 2024, 9:24pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/5 "2024-07-18T21:24:42Z")
We will see how much smarter it is or much better it is to hallucinate 😏 I remember how much buzz there was when GPT-4o came and now out there is lot of complains. But good to try. Bit off topic, but I don’t totally understand why we have two places to tell model and API, settings and LLM-section? ---
### Author: ![MachineScholar](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/machinescholar/32/424719_2.png) [@MachineScholar](https://meta.discourse.org/u/MachineScholar) #### Post date: [July 18, 2024, 9:28pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/6 "2024-07-18T21:28:49Z")
That’s a good point. I suspect the hallucination problems couldn’t have improved with this model however I managed to largely mitigate that by putting a bunch of constraints throughout the system prompt – though that has its own downsides of course. > [@Jagster](#): > > Bit off topic, but I don’t totally understand why we have two places to tell model and API, settings and LLM-section? It makes sense only for the manual LLM set up. So I find myself asking the same question 😅 ---
### Author: ![Saif](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/saif/32/318253_2.png) [@Saif](https://meta.discourse.org/u/Saif) #### Post date: [October 11, 2024, 4:12pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/7 "2024-10-11T16:12:06Z")
> [@MachineScholar](#): > > It makes sense only for the manual LLM set up. So I find myself asking the same question 😅 The idea is that you setup your LLM 1st and then pick that LLM for the Discourse AI feature of your choosing hence why they are currently in 2 separate places We have had some internal discussions regarding perhaps having this process all in one place i.e - right when you setup the LLM you can also toggle it on for the specific AI features, like how we have it for AI bot ---
### Author: ![sam](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/sam/32/102149_2.png) [@sam](https://meta.discourse.org/u/sam) #### Post date: [October 11, 2024, 8:38pm UTC](https://meta.discourse.org/t/gpt-4o-mini-landed-going-to-be-supported/317097/8 "2024-10-11T20:38:51Z")