What problem does it solve?
AI providers regularly deprecate, remove, or sunset models, leaving stale entries in Kiln's model registry that break user workflows. This Skill automates the audit of ml_model_list.py against live provider APIs to find and flag outdated models.
Core Features & Use Cases
- Multi-Provider Availability Checks: Queries model-listing endpoints for OpenRouter, OpenAI, Anthropic, Gemini, Fireworks, Together, SiliconFlow, Cerebras, Groq, and Vertex AI, handling each provider's API quirks automatically.
- Expiration and Lifecycle Detection: Surfaces OpenRouter models with upcoming expiration dates and Bedrock models with LEGACY lifecycle status, plus LiteLLM deprecation_date cross-referencing.
- Safe Deprecation Marking: Sets
deprecated=True on confirmed-removed provider entries only after user confirmation, never deleting models.
- Use Case: Before a Kiln release, run the audit to discover that
gemini-1.5-pro was removed from the Gemini API, then mark its provider entries deprecated so users stop selecting a dead model.
Quick Start
Ask the AI to check Kiln's model list for deprecated or sunset models across all providers and report which entries should be marked deprecated.