Online

ai.faisalm.dev

Private HTTP wrapper for the llama3.2:1b Ollama model with a simple browser page, health checks, API-key protection, basic rate limiting, CORS control, and an OpenAI-style chat endpoint.

Endpoints

GET /health
GET /v1/models
POST /api/generate
POST /v1/chat/completions

Defaults

Timeout: 120000ms
Context: 2048
Max tokens: 256
API key enabled: yes

CORS

*

Example request

curl -H 'Authorization: Bearer YOUR_KEY' -H 'Content-Type: application/json' \
  -d '{
    "messages": [
      {"role": "system", "content": "Be concise."},
      {"role": "user", "content": "Write a haiku about Liverpool rain."}
    ]
  }' \
  http://ai.faisalm.dev/v1/chat/completions