Can i enable GenAI with frigate add-on?

[yanivf38]

i tried to setup genai and used the default gemini-1.5-flash but when it runs i get the following error message -
"Gemini returned an error: 404 models/gemini-1.5-flash 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"

[inkeep-ai-assistant[bot]]

---

Yes, you can enable GenAI with the Frigate add-on(1). The error you're seeing suggests the model name may not be available or supported in the API version Frigate is using.

For Google Gemini, the supported vision-capable models include gemini-1.5-pro and gemini-1.5-flash(1). Try updating your configuration to explicitly specify one of these models:

genai:
  enabled: True
  provider: gemini
  api_key: "{FRIGATE_GEMINI_API_KEY}"
  model: gemini-1.5-flash

(1)(2)

Make sure you have a valid API key from Google AI Studio(1). The free tier allows 15 queries per minute, which should be sufficient for typical Frigate usage(1).

If you continue to see 404 errors, verify that the model name matches exactly what's listed in Google's documentation(1), as model availability can vary by region or API version.

📚 Sources:

1. Generative AI
2. Full Reference Config

---

Have another question? Just tag @inkeep.

[yanivf38]

I have the configuration setup exactly like the example in this replay and i get the error

[hawkeye217]

Perhaps Google deprecated Gemini-1.5? The AI linked to their documentation here: https://ai.google.dev/gemini-api/docs/models

[hawkeye217]

Looks like they were recently deprecated: https://ai.google.dev/gemini-api/docs/changelog#09-29-2025

If you can confirm another model works, I'll update the Frigate docs.

[pavelkms]

I've been using the "gemini-2.5-flash" model in frigate for about a month now.

[hawkeye217]

Thanks for confirming. I've put up a PR to update the documentation. #20462