---
title: "Parallel API / Search"
description: "Parallel tool parallel-search on looot: input fields, $0.005 per call, output shape, and code to run it with curl, JavaScript or Python."
sidebar:
  hidden: true
---

{/* Generated by scripts/generate-api-reference.mjs from data/api-reference.json. Do not edit. */}

Searches the web. The legacy Search API reference (`/v1beta/search` endpoint) is available [here](https://docs.parallel.ai/api-reference/legacy/search-beta/search), and migration guide is [here](https://docs.parallel.ai/search/search-migration-guide).

- **Tool id:** `parallel-search`
- **Provider:** [Parallel](/providers/parallel)
- **Job:** [Search the web and get ranked results](/reference/jobs/web-search) (`web.search`)
- **Price:** $0.005 per call. A call that fails at the provider costs $0.

## Inputs

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `advanced_settings` | string | no | Advanced configuration for source policy, fetch policy, and excerpt settings. May impact result quality and latency unless used carefully. When omitted, excerpts are enabled by default. |
| `client_model` | string | no | The model generating this request and consuming the results. Enables optimizations and tailors default settings for the model's capabilities. Example: "claude-opus-4-7" |
| `max_chars_total` | string | no | Upper bound on total characters across excerpts from all results. |
| `mode` | string | no | Search mode preset: supported values are `turbo`, `fast`, `basic`, and `advanced`. Turbo mode is optimized for the fastest responses. Use Fast mode for high quality search within a 1-second latency budget. Basic mode offers low latency and works best with 2-3 high-quality search_queries. Advanced mode provides higher quality with more advanced retrieval and compression. Defaults to `advanced` when omitted. |
| `objective` | string | no | Natural-language description of the underlying question or goal driving the search. Used together with search_queries to focus results on the most relevant content. Should be self-contained with enough context to understand the intent of the search. |
| `search_queries` | array | yes | Concise keyword search queries, 3-6 words each. At least one query is required, provide 2-3 for best results. Used together with objective to focus results on the most relevant content. |
| `session_id` | string | no | Session identifier to track calls across separate search and extract calls, to be used as part of a larger task. Specifying it may give better contextual results for subsequent API calls. |

## Output

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

```txt
{ usage: { name, count }[], results: { url, title, excerpts: string[], publish_date }[], metadata, warnings, search_id, session_id }
```

## Run it

Every call needs your API token in `LOOOT_TOKEN`; [Sign in](/get-started/sign-in#use-the-token-in-scripts-and-agents) 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:

<CodeGroup>

```bash curl
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":"parallel-search","input":{"search_queries":[],"client_model":"claude-opus-4-7"},"wait":30}'
```

```js JavaScript
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: "parallel-search",
    input: {
      search_queries: [],
      client_model: "claude-opus-4-7",
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);
```

```python Python
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": "parallel-search",
        "input": {
            "search_queries": [],
            "client_model": "claude-opus-4-7",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))
```

</CodeGroup>

To let looot pick among every provider of this job instead, send `job:web.search` as `endpointId`; see [the job page](/reference/jobs/web-search).