openrouter-model-routing

# OpenRouter Model Routing ## Overview OpenRouter gives you access to 100+ models through one API. The key to cost efficiency is routing each request to the right model based on task complexity, required capabilities, cost budget, and latency requirements. This skill covers task-based routing, complexity classification, cost-aware selection, and OpenRouter's native routing features. ## Task-Based Router ```python import os, re from openai import OpenAI client = OpenAI( base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"], default_headers={"HTTP-Referer": "https://my-app.com", "X-Title": "my-app"}, ) # Model tiers by cost and capability MODELS = { "free": "google/gemma-2-9b-it:free", # $0/0 — testing only "budget": "meta-llama/llama-3.1-8b-instruct", # $0.06/$0.06 per 1M "mid": "openai/gpt-4o-mini", # $0.15/$0.60 per 1M "standard":"anthropic/claude-3.5-sonnet", # $3/$15 per 1M "premium": "openai/o1", # $15/$60 per 1M } TASK_ROUTING = { "classification": "budget", # Simple label assignment "translation": "mid", # Moderate quality needed "summarization": "mid", # Good quality, cost-effective "code_generation": "standard", # Needs high accuracy "code_review": "standard", # Needs reasoning "analysis": "standard", # Complex reasoning "creative_writing":"standard", # Quality matters "de...