# modelright — agent interface
Live registry of AI model specifications, context windows, and per-1M-token pricing across providers, synced hourly from OpenRouter with Artificial Analysis enrichment.

## Preferred interface
MCP over Streamable HTTP:
  POST https://modelright.dev/api/mcp
  (also mounted at POST https://modelright.dev/.well-known/mcp)
  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).

## REST fallback
  GET https://modelright.dev/api/v1/models[?provider=&modality=&status=&minContext=&maxInputPrice=&freeOnly=&sort=&limit=&offset=]
  GET https://modelright.dev/api/v1/models/{provider}/{slug}
  GET https://modelright.dev/api/v1/providers
  GET https://modelright.dev/api/v1/changes[?days=1-90]
  GET https://modelright.dev/api/models/search?q={term}
  GET https://modelright.dev/openapi.json (also /.well-known/openapi.json)

## Auth
none — all read endpoints are unauthenticated; POST /api/ingest requires `Authorization: Bearer <INGEST_TOKEN>`

## Rate limits
  MCP: 60-request burst, ~1 request/second sustained, per IP
  Ingest: 10-request burst, ~1 request/second sustained, per token

## House rules
  - Read-only; no write tools are exposed to agents.
  - Prices are USD per 1M tokens; data refreshes hourly from OpenRouter.
  - Pair-wise compare pages live at /compare/{provider--slug}-vs-{provider--slug}.

See https://modelright.dev/llms.txt for the human-readable summary.