Model fallback configuration - unable to select workspace configured models

Hey,

I am working on setting up the LangSmith LLM Gateway. When I am working to configure a fallback route for the models I cannot seem to build the chain as I cannot select any configured models.

I’ve added a screenshot to show what I am looking at:

Also here’s another screenshot showing I have model configurations:

Any help would be greatly appreciated!

hi @sa64r

hmm have you tried with an “OpenAI Compatible Endpoint” or “Anthropic” configuration?

All model configurations other than OpenAI Compatible Endpoint or Anthropic are filtered out of the fallback-chain picker - that’s why it shows up empty. See the Model fallbacks docs, “Wire formats” section:

“Only these two provider types can go in a chain. A model configuration saved for another provider, such as Azure OpenAI or Bedrock, isn’t eligible. To reach a host that speaks the OpenAI API, save it as an OpenAI Compatible Endpoint with its base URL.”

Created this config and still do not see the model appearing in the UI for selection

this one, not “Open AI”: