Call Ollama from Code

Start the API server

ollama serve

The API is available at:

http://localhost:11434

Generate with curl

curl http://localhost:11434/api/generate -d '{
  "model": "llama3.2",
  "prompt": "Write a Python function that reverses a string",
  "stream": false
}'

Generate with Python

import requests

r = requests.post("http://localhost:11434/api/generate", json={
    "model": "llama3.2",
    "prompt": "Write a Python function that reverses a string",
    "stream": False
})
print(r.json()["response"])

Streaming responses

Set

"stream": true

and iterate over response chunks for real-time output.

Chat endpoint

For multi-turn conversations, use the chat API:

curl http://localhost:11434/api/chat -d '{
  "model": "llama3.2",
  "messages": [
    {"role": "user", "content": "Hello"}
  ],
  "stream": false
}'

Connect your IDE

Both Claude Code and Cursor accept a custom OpenAI-compatible URL. Point them to:

http://localhost:11434/v1