Today found：
Trying to contact the model returned this error: { "error": { "code": 404, "message": "models/embedding-001 is not found for API version v1beta, or is not supported for embedContent. Call ListModels to see the list of available models and their supported methods.", "status": "NOT_FOUND" } }
In Discourse AI：
hmmm, i use Gemini’s gemini-embedding-001 as well and mine is working as expected with no errors.
what are your other settings:
you might not have the model set in AI_embeddings_selected_model…?
i don’t even have the text-embedding-3-small option. is that from another model? nevermind, that is the OpenAI one. All my AI is setup on Google cloud with gemini. the only option for embedding i have is the Gemini's embedding-001 model. 
oh hey i am now getting something similar with gemini-2.5-flash-image (nanobanana) - this just happened:
Trying to contact the model returned this error: { "error": { "code": 404, "message": "models/gemini-2.5-flash-image-preview is not found for API version v1beta, or is not supported for generateContent. Call ListModels to see the list of available models and their supported methods.", "status": "NOT_FOUND" } }
all my other gemini flash models appear to be working
edit: ok i fixed it. the url of some of the gemini image models have changed and needed to be updated in URL of the service hosting the model field
for the embedding model it should be https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:embedContent
i don’t know in your case, other than just make sure the url is correct for the embedding model? i just updated the fields for the ones that changed. i didn’t update my instance.
yea that was the field i meant by url. sorry i should have been more clear. glad you fixed it! 
