How do I connect Google Cloud AI for Discourse AI. I tried the steps mentioned in the post [image] Set up Gemini API Keys for Discourse AI Integrations How to Set Up Gemini API Keys for Discourse AI Introduction This topic covers how to set up your Google Gemini API key with an existing Google Cloud account project. Gemini is not a free service, and therefore, you will need to ensure you have billing configured in your Google Cloud admin. There is some important information with links in the Gemini Developer studio key generating page about this: [The image is a screenshot of a text document that appears to be instructions for using the… but GCP interface has changed. I tried what’s mentioned at [image] Setting up a Gemini API key on a Google Cloud service account Documentation ai gemini How to set up a Gemini api key on a Google Cloud service account Step 1: set up the service account go to your Google Cloud IAM and admin page and select +create service account at the top menu: follow the prompts and fill out the info: ... But still encountering the following error [image] [image] For now I’m using a workaround (Google Cloud Run → vLLM) but latency is very high with that method. Can someone tell me how do I fix this error? I want to use one of the AI models available on GCP as the default LLM.

[image] Karthik_K1: @atonotdead Do you experience any latency with LiteLLM method? Not at all, and I also used a Nginx internal proxy with a script to rotate the token login on Vertex. LiteLLM is really good if you have plans to deploy more keys, MCP servers and want to use more LLM endpoints. You can use almost any subscription tier as LLM API with it.

I used it ln Discourse through LiteLLM proxy. They offer 300 USD in free bonus credits.

@Lilly I also have credits in GCP that’s why I’m trying to connect via Vertex. @satonotdead Do you experience any latency with LiteLLM method?

i’ve never set it up using vertex. it works perfectly fine though using gemini api service. i just walked through the configuration and i see no change in the google cloud dashboard for the apis and services and for configuration of credentials. :woman_shrugging:t2:

[image] Karthik_K1: [image] image1052×172 27.5 KB did you see the documentation that is quoted there? what does it tell you?

If I use the Gemini method, it will not use the credits I have because it will connect me to Gemini AI Studio, which cannot utilize the credits in GCP. [image] [image]

[image] Karthik_K1: Gemini AI Studio i don’t even use this

Can you share a screenshot of your configuration?

i just did a new configuration of gemini flash 3.6 and all i had to add to do was set the api key to use (which in my case is called 2026-07-02). i didn’t change anything else from the default setup for flash 3.6 and it tested successfully and worked fine: [Screenshot 2026-09-03 at 7.28.53 PM] [Screenshot 2026-09-03 at 7.29.21 PM] but the api key credential is using the gemini api service, not vertex. my GCP configuration looks exactly like what you linked in the disco-docs screenshots (those are screenshots of my GCP config!).

Yes, this method works, but it will not allow me to use the GCP credits I already have.

Solving Gemini API key errors in Discourse

Product Support Self-hosting

Karthik_K1 (Karthik K) September 5, 2026, 5:53am 17

Closing this topic, though the Vertex method is not working, as the LiteLLM workaround is fine.

Topic		Replies	Views
Set up Gemini API Keys for Discourse AI Integrations how-to , ai	2	1156	August 6, 2026
Discourse AI Gemini Embeddings Failing to Enable, But Other Features Work Fine Product Support ai	1	238	November 7, 2024
How to fix 401 errors with Gemini embeddings Product Support embedding , ai	2	250	July 16, 2026
Configure API Keys for OpenAI Integrations how-to , ai	11	4425	November 11, 2024
Configuring Discourse AI with internal OpenAI APIs Product Support ai	14	486	August 19, 2026

Solving Gemini API key errors in Discourse

Related topics