# modelright

> Modelright tracks AI model specifications, pricing, availability, and snapshots across providers.

## Main Routes
- /models : Full list of AI models with pricing and context windows
- /providers : Provider index; /providers/{slug} for per-provider model lists
- /pick : Curated top-10 task picks index
- /pick/{task} : Top-10 model picks per task; task is one of: long-context, vision, cheap-bulk, chat, coding
- /rankings : Leaderboards ranked by Artificial Analysis benchmarks (intelligence index, coding index, output tok/s, TTFT) joined to live $/1M pricing
- /compare : Side-by-side spec and price comparison tool
  - /compare?m={provider/slug},{provider/slug},... : ad-hoc comparison of 2+ models
  - /compare/{a}-vs-{b} : canonical pair pages, e.g. /compare/openai--gpt-4o-vs-anthropic--claude-sonnet
- /changes : Recent catalog changes
- /calculator : Cost calculator — tokens in/out and requests/day to estimated spend
- /api : API documentation with examples

## REST API
- GET /api/v1/models : JSON list of all models (filters: provider, modality, status, minContext, maxInputPrice, freeOnly, sort, limit, offset)
- GET /api/v1/models/{provider}/{slug} : JSON model detail including last 30 price snapshots
- GET /api/models/search?q= : fuzzy model name search
- GET /changes/rss.xml : RSS feed of catalog changes
- GET /openapi.json : OpenAPI 3.1 document (also /.well-known/openapi.json)

## MCP (agent interface)
- POST /api/mcp : MCP over Streamable HTTP (Accept: application/json, text/event-stream). Tools:
  - list_providers: List providers tracked by the registry with their model counts. Use provider slugs in list_models / get_model / compare_models.
  - search_models: Substring search across model name, slug, and provider — the fast path to a model's provider/slug pair for the detail tools.
  - list_models: List tracked models with pricing and context windows. Filter by provider, modality tag, status, or price/context bounds.
  - get_model: Full detail for one model (provider+slug from search_models): specs, current price, status, and recent price/availability snapshots.
  - compare_models: Side-by-side comparison of 2-10 models by provider/slug: context window, input/output price per 1M tokens, modalities, status.
  - get_ingest_status: Data-freshness check: registry totals and the most recent ingest runs (source, model count, status, time).

## Agent discovery
- /.well-known/agent-card.json : A2A agent card listing skills 1:1 with the MCP tools
- /.well-known/mcp/server-card.json : Smithery-format MCP server card
- /agents.txt : Plain-text agent interface summary