Fallback not working if model from other provider

[gwpl]

I defined in settings as fallback , model from other provider and it does not work:

$ mods -m o1-mini 'test'

   ERROR  openai API request error.  

  error, status code: 400, message: Your organization must qualify for at least usage tier 5 to access 'o1-mini'. See https://platform.openai.com/docs/guides/rate-limits/usage-tiers for more details on usage tiers.

What I wanted to achieve:

• define config for OpenAI o1-mini , that will use it once I am granted access, and until then to fallback to model of other provider.

[caarlos0]

yes, right now fallbacks are only available between the same provider.

[thedenisnikulin]

@caarlos0 I think it would be a good idea to be able to provide a general fallback list in the config, using the models/aliases listed in apis cfg