Ollama runs open models on your computer and serves a REST API at http://localhost:11434. Pull a model first (ollama pull <model>); {{MODEL}} is any model you have.
None — it's your own machine. To call it from a web page like PostTaco, allow the page's origin: start Ollama with OLLAMA_ORIGINS=https://posttaco.dev, or use the PostTaco extension.
Full reference: https://github.com/ollama/ollama/blob/main/docs/api.md
curl http://localhost:11434/api/tags
stream: false returns one JSON object instead of a stream of lines.
curl http://localhost:11434/api/generate \
-H "Content-Type: application/json" \
-d '{"model": "{{MODEL}}", "prompt": "Why is the sky blue?", "stream": false}'
curl http://localhost:11434/api/chat \
-H "Content-Type: application/json" \
-d '{"model": "{{MODEL}}", "messages": [{"role": "user", "content": "Hello!"}], "stream": false}'