llms.txt
Compare with other sites' llms.txt files →# StoreRouter
> Ecommerce data for AI agents. One API for all stores. Search across stores, parse any product page, and find alternatives — in one enriched schema agents can comprehend without scraping.
Two different jobs bring an agent here. Pick the one that matches yours.
**Building something with product data** — read the onboarding skill first. It
tells you how to get a credential and which call to make; everything else here
is reference material you will not need until you have a key.
**Running a store, and want it on StoreRouter** — load the merchant skill at
https://dev.storerouter.ai/merchant-onboarding/SKILL.md. It signs your human up as
the store's Merchant organization and gets the catalog covered.
Every `/v1` endpoint requires an organization API key (`octo_live_...`) on a
Developer organization. There is no credential-free tier: a request with no
`Authorization` header is refused with `401` on every route. A coding agent
gets a key by opening a `/cli-auth` session, printing one URL for its human to
authorize in a browser, and polling for the key; the human can also create the
key by hand at https://dev.storerouter.ai. Either way a human authorizes in a
browser — accounts and organizations are never created programmatically.
## Start here
- [Agent onboarding SKILL.md](https://dev.storerouter.ai/agent-onboarding/SKILL.md): How to get a StoreRouter API key, verify it, and choose between direct `/v1` calls, an application integration, MCP, and requesting coverage of a new merchant.
- [Merchant onboarding SKILL.md](https://dev.storerouter.ai/merchant-onboarding/SKILL.md): For the person who runs a store. Sign up as the store's Merchant organization, connect Shopify if the store runs on it, and get the catalog covered.
## What StoreRouter does
- [Search](https://storerouter.ai/products/search): Agentic web search finds pages. StoreRouter finds products. Web search APIs return links and snippets. Your agent still has to open each page, pull out the product, and check whether it actually matches. StoreRouter searches the catalogs themselves, so every result is a product you can filter, sort and compare.
- [Live catalog](https://storerouter.ai/catalog-coverage): Crawlers fetch pages. StoreRouter is a live catalog. A crawler returns page markup, and leaves the rest to you: parse fields, wrangle per-site schema, schedule refreshes, enrichment and indexing. StoreRouter abstracts all of that away into a live catalog.
- [One product schema](https://cdn.storerouter.ai/openapi/platform/v1/openapi.json): Every store describes products its own way. StoreRouter keeps the facts, and adds meaning. Every product keeps the store's own facts, mapped into one schema, then gets the attributes the page only implies, for its category: fit for a dress, skin type for a moisturizer, notes for a perfume, upholstery for a sofa. More for your agent to search, filter and compare on, across every store. From the store: title, price & sale price, variants, per-size stock, images, product URL. Normalized: canonical brand, taxonomy path, color family, currency. Enriched by StoreRouter, by category: apparel (fit, fabric, neckline, length, pattern, occasion); beauty (skin type, cosmetic function, product form, ingredients, certifications); fragrance (fragrance family, top notes, heart notes, base notes, scent); furniture (upholstery material, tabletop material, leg material, seat type, backrest type); media (genre, music genre, cover type, language, audience); + more.
- [Lookup and parse](https://storerouter.ai/products/parse): Ditch the browser. 100× faster, 500× cheaper. StoreRouter reads each store with code, not a model. One call returns the product, structured and enriched, in about 100 ms, and the same call returns the same answer every time. Cost compares StoreRouter's $2 per 1,000 lookups with an LLM reading the page at ~$1.25 per million input tokens.
- [Self-healing catalogs](https://storerouter.ai/catalog-coverage): That's our problem, not yours. Scrapers break silently when a store changes. StoreRouter keeps answering the same way.
- [Pricing](https://storerouter.ai/docs/guides/pricing-and-billing): Pay per successful request. No subscriptions and no seat fees. Every organization gets free credit each month; top up when you need more. Lookup & Parse: $2 per 1,000 requests; Search: $14 per 1,000 requests; Free credit: $5 every month. Only successful 2xx responses are billed. Purchased credit never expires.
## Read a covered product as Markdown
For a published selection of crawled products, read a product page on the
StoreRouter website without an API key. For example:
- [Veda Celine Jacket](https://storerouter.ai/catalog-coverage/stores/thereformation/products/veda-celine-jacket-00a3f838-f82a-57e2-b9c7-3e607c583259.md)
- [Reformation products as Markdown](https://storerouter.ai/catalog-coverage/stores/thereformation/products.md)
A store's `data.md` links to its published product pages and `products.md`
index. This selection is a subset of its catalog; price and availability may
change. Every `/v1` call still requires an API key.
## Compare
How StoreRouter differs from scraping platforms, web data APIs, product
databases and product search APIs, and when each one fits. [All comparisons](https://storerouter.ai/compare).
- [StoreRouter vs. Apify](https://storerouter.ai/compare/apify)
- [StoreRouter vs. Bright Data](https://storerouter.ai/compare/bright-data)
- [StoreRouter vs. Channel3](https://storerouter.ai/compare/channel3)
- [StoreRouter vs. Datafiniti](https://storerouter.ai/compare/datafiniti)
- [StoreRouter vs. Firecrawl](https://storerouter.ai/compare/firecrawl)
- [StoreRouter vs. Oxylabs](https://storerouter.ai/compare/oxylabs)
- [StoreRouter vs. ScraperAPI](https://storerouter.ai/compare/scraperapi)
- [StoreRouter vs. Shopify Catalog](https://storerouter.ai/compare/shopify-catalog)
- [StoreRouter vs. Zyte](https://storerouter.ai/compare/zyte)
## Guides
Vendor-neutral answers to common product-data questions, with the tools for each
compared. [All guides](https://storerouter.ai/guides).
- [How do you normalize product data from different retailer websites into one schema?](https://storerouter.ai/guides/normalize-product-data-across-retailers): Target schema, field mapping, GTIN and variant matching, units and categories, and keeping it fresh.
- [How do you build a price comparison tool with live product data from multiple stores?](https://storerouter.ai/guides/build-a-price-comparison-tool): Finding offers, matching the same product across stores, variant-level prices, and refresh strategy.
## API reference
- [Platform Catalog API v1 (OpenAPI)](https://cdn.storerouter.ai/openapi/platform/v1/openapi.json): The complete, machine-readable `/v1` contract — every endpoint, schema, and enum. This is the source of truth; generate a client from it rather than hand-rolling requests. There is no `llms-full.txt`: a hand-maintained flattening of this file would only drift away from it.
- [Protected resource metadata](https://api.storerouter.ai/.well-known/oauth-protected-resource): RFC 9728 metadata for the `/v1` data plane, and the target of the `WWW-Authenticate` challenge `/v1` returns on a 401.
## MCP
- [StoreRouter MCP server](https://mcp.dev.storerouter.ai/mcp): Streamable HTTP MCP endpoint with OAuth 2.1, PKCE, and Dynamic Client Registration. Add it with `claude mcp add --transport http storerouter https://mcp.dev.storerouter.ai/mcp`; no API key needed.
- [MCP protected resource metadata](https://mcp.dev.storerouter.ai/.well-known/oauth-protected-resource): RFC 9728 metadata naming the authorization server for the MCP surface.
## Credentials
- [Agent credential handoff](https://dev.storerouter.ai/api/auth/cli/start): `POST` a PKCE S256 `code_challenge` to open a 10-minute authorization session; the response carries the `authorize_url` to print for your human. Poll `https://dev.storerouter.ai/api/auth/cli/status` with the `code_verifier` to collect the key once. Full walkthrough in the SKILL.md above.
- [StoreRouter Platform](https://dev.storerouter.ai): Sign in or create an account, then create or select a **Developer** organization. API keys live at `/<org-slug>/api-keys`, where they can also be revoked — including keys a coding agent was authorized to receive.
## Crawler
- [StoreRouterBot](https://storerouter.ai/bots): User agent, Web Bot Auth verification, and contact details for the crawler that builds these catalogs. Relevant if you operate a site StoreRouter crawls, not if you are consuming the API.