We improved the UI a lot in the past week, can you try it out again?

Been supported for quite a while.

I seem to have an issue where I cannot Select a LLM even though I have the CDCK hosted ones configured.. is this normal?

A lot to unwrap here, which llm are you trying to choose for what? The CDCK LLMs are only available for very specific features, to see which you need to head to /admin/whats-new on your instance and click “only show experimental features”, you will need to enable them to unlock the CDCK LLM on spec…

Is there also a topic that provides a general rundown of the best cost/quality balance? Or even which LLM can be used for free for a small community and basic functionality? I can dive into the details and play around. But I’m a bit short in terms of time. For example, I only care about spam detect…

[image] AquaL1te: Is there also a topic that provides a general rundown of the best cost/quality balance? Or even which LLM can be used for free for a small community and basic functionality? I can dive into the details and play around. But I’m a bit short in terms of time. We do have this to…

Done! It was indeed pretty easy. But maybe for a non techie it may still be a bit hard to setup. For example, the model name was automatically set in the settings, but wasn’t the correct one. Luckily I recognized the model name in a curl example for Claude on the API page and then it worked :tada: E…

[image] AquaL1te: For example, the model name was automatically set in the settings, but wasn’t the correct one. Which one did you pick for Claude? What was the incorrect name shown, and what did you correct it to?

I use Claude 3.5, the model ID is by default claude-3-5-haiku, but I had to change it to claude-3-5-haiku-20241022, otherwise I got an error.

[image] AquaL1te: I use Claude 3.5, the model ID is by default claude-3-5-haiku, but I had to change it to claude-3-5-haiku-20241022, otherwise I got an error. Good to note, yeah sometimes there might be a disconnect. The auto-populated info should act as guidance, which tends to work most of…

[image] Discourse AI - Large Language Model (LLM) settings page Gemini Flash 2.0 This model is not listed on 3.4.2 - are those pre-configs only available on 3.5 and I have to add them manually? Edit: Also what option do I choose for “Tokenizer” when using Grok 3 models? [Screenshot 2025-04…

Random discussion about Discourse LLM setup

Support

sam (Sam Saffron) August 20, 2026, 6:16am 21

Gemini 3.7 flash and (2.5 flash and up) work fine now, use interactions API.

Grok should work fine it uses completion api afaik.

Topic		Replies	Views
Discourse AI - Large Language Model (LLM) settings page Site Management how-to , ai	1	4206	September 30, 2024
What LLM to use for Discourse AI? Site Management how-to , ai	0	952	January 23, 2025
What's the cheapest/best AI to use for AI Spam? Support ai , spam	6	420	March 18, 2025
How to configure Discourse to use a locally installed LLM? Support ai	7	397	June 3, 2025
Estimating costs of using LLMs for Discourse AI Site Management how-to , price-sensitive , ai	2	1176	November 14, 2024

Random discussion about Discourse LLM setup

Related topics