API giving me a model version lower the requested

[JordanDDisch]

When specifing which model I want I want in the dropdown, i've been getting a model that is not the same as the one selected. I've reinstalled Librechat with the new code from main and refreshed all the docker dependencies as well.

I'm testing the model by asking when its training data is cut off and lining it up to Anthropics models knowledge dates: https://support.anthropic.com/en/articles/8114494-how-up-to-date-is-claude-s-training-data. Strangely i'm also seeing the same results by directly hitting the API with curl. Is this user error or Anthropic being cheeky?

curl https://api.anthropic.com/v1/messages \ --header "x-api-key: ${key}" \ --header "anthropic-version: 2023-06-01" \ --header "content-type: application/json" \ --data \ '{ "model": "claude-opus-4-1-20250805", "max_tokens": 1024, "messages": [ {"role": "user", "content": "when does your training data end ?"} ] }' {"id":"msg_014ajN9PsRNLY82Zhy7P5rnV","type":"message","role":"assistant","model":"claude-opus-4-1-20250805","content":[{"type":"text","text":"My training data has a cutoff date of April 2024. This means I have knowledge of events, information, and developments up until that point, but I'm not aware of anything that has happened after April 2024."}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":14,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":50,"service_tier":"standard"}}