[Bug]: model: fireworks_ai/accounts/fireworks/models/deepseek-r1 gives 400 error in version v1.61.11

[numenbit]

What happened?

Testing the chat with this existing model gives a 400 error below this was working in version main-v1.59.8. My proxy config is this

• model_name: deepseek-r1
  litellm_params:
  model: fireworks_ai/accounts/fireworks/models/deepseek-r1
  api_key: secret

Did anything change that might cause this. I dont see deepseek as a support model for fireworks I believe it was there before. Can I just make this an open ai compatible model?

Relevant log output

itellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=deepseek-r1
 Pass model as E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/starcoder',..)` Learn more: https://docs.litellm.ai/docs/providers

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

v1.61.11

Twitter / LinkedIn details

No response