keirouter-web-fetch

KeiRouter — Web Fetch

Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.

Discover

curl $KEIROUTER_URL/v1/models/fetch | jq '.data[].id'
curl "$KEIROUTER_URL/v1/models/info?id=firecrawl/firecrawl-scrape"

model is provider/model (e.g. firecrawl/firecrawl-scrape), a chain name that lists several fetch providers for automatic fallback, or an alias.

Endpoint

POST $KEIROUTER_URL/v1/web/fetch

Field	Required	Notes
model	yes	from /v1/models/fetch
url	yes	URL to extract
format	no	markdown (default) / text / html
max_characters	no	truncate output

Examples

Firecrawl

curl -X POST $KEIROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $KEIROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"firecrawl/firecrawl-scrape","url":"https://example.com","format":"markdown"}'

Tavily

curl -X POST $KEIROUTER_URL/v1/web/fetch \
  -H "Authorization: Bearer $KEIROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tavily/tavily-extract","url":"https://example.com","format":"markdown"}'

JS:

const r = await fetch(`${process.env.KEIROUTER_URL}/v1/web/fetch`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.KEIROUTER_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "exa/exa-contents", url: "https://example.com", max_characters: 5000 }),
});
const page = await r.json();
console.log(page.title, page.content.length);

Response shape

{
  "url": "https://example.com",
  "title": "Example Domain",
  "content": "# Example Domain\n...",
  "format": "markdown"
}

The X-KeiRouter-Provider header names the provider that answered.

Provider quick reference

Provider	model	Best for
Firecrawl	firecrawl/firecrawl-scrape	JS-rendered pages, format=markdown/html
Tavily	tavily/tavily-extract	Bulk extract
Exa	exa/exa-contents	Pre-indexed pages; fast text extraction