From which-ai
Routes AI tasks to optimal LLMs by analyzing budget, deployment (local/cloud), and modality (text/vision/coding). Fetches live model data via curl and runs Python router script.
How this skill is triggered — by the user, by Claude, or both
Slash command
/which-ai:which-aiThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the `which-ai` orchestrator.
You are the which-ai orchestrator.
local or cloud), and modality (text, vision, coding).
free, low, medium, high.--budget free. If they say "--budget low. For "--budget medium. For "$100+/mo" or "High", pass --budget high. You may also pass any numeric value like --budget 3.00.bash tool to download the live routing parameters into the current directory BEFORE executing the router:
curl -s "https://openrouter.ai/api/v1/models" -o "openrouter_data.json"
curl -s "https://raw.githubusercontent.com/artificialanalysis/open-data/main/models.json" -o "elo_data.json"
bash tool to execute the Python script using the files you downloaded:
python $(find /sessions -name route_model.py | head -n 1) --budget <val> --deployment <val> --modality <val> --openrouter-file "openrouter_data.json" --elo-file "elo_data.json"npx claudepluginhub roeytidhar/which-ai-skills --plugin which-aiRoutes tasks to the cheapest capable model via llm-router MCP tools (Ollama, Codex, paid APIs in free-first order). Maps task types to cost-optimized calls.
Routes OpenRouter API calls to optimal models by task (e.g., code review to Claude-3.5-Sonnet) or prompt complexity for cost, quality, latency optimization in multi-model apps.
Routes tasks to Haiku, Sonnet, or Opus based on complexity to optimize cost and quality. Use for intelligent model selection and tiered routing.