Jina Search API / Search the web

Jina Reader API tool jina-search on looot: input fields, $0.0025 per call, output shape, and code to run it with curl, JavaScript or Python.

Searches the web for a query and returns results in search-engine order, formatted for LLMs. Send q; num, page, gl, hl and location refine it.

Tool id: jina-search
Provider: Jina Reader API
Job: Search the web and get ranked results (web.search)
Price: $0.0025 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`gl`	string	no	Two-letter country code for the search.
`hl`	string	no	Two-letter language code for the search.
`location`	string	no	City-level location the search should appear to originate from.
`num`	number	no	Maximum results to return. Using num may raise latency and token cost.
`page`	number	no	Result offset, for pagination.
`q`	string	yes	Search query. Example: “example keyword”
`accept`	string	no	Must be application/json – forces the gateway to send Accept: application/json so Jina returns structured JSON instead of markdown.

Output

Shape of the run’s result, checked against 2 real answers:

{ code, data: { url, date, title, usage: { tokens, outputTokens, scaledTokens, measuredTokens }, content, warning, external: { icon: { ... }, search: { ... }, EditURI: { ... }, license: { ... }, preload: { ... }, manifest: { ... }, alternate: { ... }, canonical: { ... }, dns-fetch: { ... }, preconnect: { ... }, dns-prefetch: { ... }, apple-touch-icon: { ... }, compression-dictionary: { ... } }, metadata: { lang, title, og:url, robots, bingbot, og:type, keywords, og:image, og:title, referrer: string[], viewport, generator, og:locale, al:ios:url, description, theme-color, twitter:url, color-sche... ...

The shape is cut here. Signed in, looot inspect jina-search prints all of it.

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"jina-search","input":{"q":"example keyword"},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "jina-search",
    input: {
      q: "example keyword",
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "jina-search",
        "input": {
            "q": "example keyword",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:web.search as endpointId; see the job page.

Jina Search API / Search the web

Inputs

Output

Run it