List language models accessible through a Claude Code Router instance.
npx skills add https://github.com/npow/claude-skills --skill ccr-models
Please help me install this Agent Skill. Skill: ccr-models Source: https://github.com/npow/claude-skills/tree/main/ccr-models Command: npx skills add https://github.com/npow/claude-skills --skill ccr-models
This Skill removes the guesswork from discovering which language models are currently accessible through a running Claude Code Router instance.
Ask the ccr-models skill to list all models currently available through the running Claude Code Router.
High-intent search queries and answers about installing and using this skill.
To list available models through a Claude Code Router, you query the router's local models API endpoint. This discovers all accessible language models and groups returned identifiers by Claude proxy and Model Gateway provider.
Model discovery in Claude Code configuration workflows is the process of querying a running router to identify exact language model identifiers. It separates Claude proxy models from Model Gateway models to streamline endpoint selection and configuration.
Yes, you need a running Claude Code Router with an accessible local models API to discover accessible LLM endpoints. The router acts as the gateway, querying its models endpoint to return and group available language model identifiers.
Provider comparison for models accessible via a model gateway works by grouping returned identifiers based on their source. It separates Claude proxy models from Model Gateway models, allowing you to easily compare and select the exact endpoints available for your workflow.
Discovered models are grouped by Claude proxy and gateway provider to remove guesswork during model selection. This grouping clarifies which language models are currently accessible through the running Claude Code Router instance for easier endpoint comparison.
open-octoConfigure octo providers, models, API keys, and agent defaults via REST API.
dtyqList available large language models and send chat completion requests from code.
AveerOrchestrate deployment and configuration of local LLM inference servers for OpenCode.
Extremez-SuryaManage AI model routing, provider failover, cost tracking, and authentication for Vercel AI Gateway.
