litellm --model ollama/llama3.3 --port 8000

Category: AI Agents & MCP

litellm --model ollama/llama3.3 --port 8000

Start a LiteLLM proxy server for local model access

Runs a local OpenAI-compatible API proxy that routes to Ollama or any configured backend. Any tool that speaks the OpenAI API (including many agent frameworks) can now use your local model without code changes. Useful for testing locally before switching to cloud.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.