[feature request] LiteLLM support

[tobwen]

feature request

Would it be possible to add LiteLLM support?

benefits

• more than 100 LLMs would be accessable
• retry/fallback logic across multiple deployments
• track spend & set budgets

advantages

• LiteLLM is self-hosted and actively developed
• huge advantage: LiteLLM offers a OpenAI-compatible API, so there aren't much changes needed to the code base
• others would take care of developing the API interface and you can concentrate fully on the UI

[deep93333]

@tobwen Soon we'll add support for custom proxy server endpoint through which you'll be able to use LiteLLM

[ishaan-jaff]

Hi @tobwen , thanks for using LiteLLM. Any chance we can hop on a call to learn how we can improve LiteLLM Proxy for you ?

We’re planning roadmap and I’d love to get your feedback

• my cal for your convenience: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat
• my linkedin if you prefer DMs: https://www.linkedin.com/in/reffajnaahsi/