Jina Search Foundation API / Classify

Jina Reader API tool jina-classify on looot: input fields, $0.0002 per call, output shape, and code to run it with curl, JavaScript or Python.

Classify text or images into categories. Zero-shot and few-shot classification. Zero-shot uses embedding similarity, few-shot uses a trained classifier.

Tool id: jina-classify
Provider: Jina Reader API
Job: Sort texts into your own labels (text.classify)
Price: $0.0002 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`classifier_id`	string	no	ID of the trained classifier to use.
`input`	unknown	yes	Text to classify: a string, `TextDoc`, or list of up to 512 items.
`labels`	unknown	yes	Candidate labels: a list of up to 512 labels, or a dict of up to 8 groups with max 64 labels each.
`model`	string	yes	The code embedding model to use. Example: “jina-embeddings-v3”

Output

The run’s result holds the provider’s answer. Signed in, looot inspect jina-classify prints its fields.

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-classify","input":{"model":"jina-embeddings-v3","input":["I love this product"],"labels":["positive","negative"]},"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-classify",
    input: {
      model: "jina-embeddings-v3",
      input: ["I love this product"],
      labels: ["positive", "negative"],
    },
    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-classify",
        "input": {
            "model": "jina-embeddings-v3",
            "input": ["I love this product"],
            "labels": ["positive", "negative"],
        },
        "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:text.classify as endpointId; see the job page.

Jina Search Foundation API / Classify

Inputs

Output

Run it