litellm

Call 100+ LLMs using the OpenAI Input/Output Format

• Translate inputs to provider's endpoints (/chat/completions, /responses, /embeddings, /images, /audio, /batches, and more)
• same response format regardless of which provider you use
• Retry/fallback logic across multiple deployments (e.g. Azure/OpenAI)
• Track spend & set budgets per project