LiteLLM vs Ollama

import litellm

response = litellm.completion(
  model="gpt-4o",
  messages=[{"role": "user", "content": "Hello!"}]
)

# Same code works for claude-3-5-sonnet, gemini/gemini-pro, etc.
print(response.choices[0].message.content)

# Pull and run a model
ollama pull llama3.2
ollama run llama3.2

# Or call via REST API
curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "Hello!"
}'