Pareto Code Router

Implements a preference-based model router that automatically selects from a curated pool of coding-specialized models based on a user-specified `min_coding_score` parameter. The router evaluates available models against this threshold and picks the strongest performer meeting the criteria, eliminating the need for users to manually select between Claude, GPT-4, Llama, or other coding models. This abstraction layer sits atop OpenRouter's multi-model infrastructure, using internal benchmarking scores to make real-time routing decisions.

Enables users to express a single quality preference (`min_coding_score`) that OpenRouter maps to an internal pool of models ranked by coding capability and cost efficiency. The router selects the lowest-cost model meeting the threshold, optimizing API spend while maintaining a quality floor. This works by maintaining a ranked model registry where each model has both a coding score and cost metric, allowing the router to pick the Pareto-optimal choice for the given constraint.

Provides a single API endpoint that abstracts away differences between Claude, GPT-4, Llama, and other coding models, allowing users to make requests without knowing which underlying model will handle them. The router normalizes request/response formats across models with different tokenization, context windows, and API signatures, translating user inputs into the appropriate format for the selected model and normalizing outputs back to a standard format.

Allows users to express coding preferences declaratively (via `min_coding_score`) rather than imperatively selecting a specific model. The router interprets this preference, evaluates the current model pool against it, and makes the selection automatically. This eliminates the need for users to write conditional logic, A/B testing frameworks, or model selection algorithms in their application code.