AI visibility

Parameters

Query parameters

Examples

Make the request

curl "https://www.monocrawl.com/v1/panorama/ai-visibility?brand=My%20Brand" \
  -H "x-api-key: mn_your_key_here"

const key = process.env.MONOCRAWL_API_KEY;
if (!key) throw new Error('Set MONOCRAWL_API_KEY on your server.');
const res = await fetch(
  "https://www.monocrawl.com/v1/panorama/ai-visibility?brand=My%20Brand",
  { headers: { "x-api-key": key } },
);
const body = await res.json();

if (!body.success) {
  // one error shape for every endpoint — see /docs/errors
  throw new Error(`${body.error.type}: ${body.error.message}`);
}

console.log(body.data, "credits left:", body.credits_remaining);

import os
import requests

res = requests.get(
    "https://www.monocrawl.com/v1/panorama/ai-visibility?brand=My%20Brand",
    headers={"x-api-key": os.environ["MONOCRAWL_API_KEY"]},
    timeout=60,
)
body = res.json()

if not body["success"]:
    # one error shape for every endpoint — see /docs/errors
    raise RuntimeError(f"{body['error']['type']}: {body['error']['message']}")

print(body["data"], "credits left:", body["credits_remaining"])

Response

Response fields and example

This example is illustrative, not a captured live response. Variable-cost operations may settle a charge different from the list price below. A successful response puts the platform payload in data and reports the exact credits used, remaining balance, request id and cache status beside it.

{
  "success": true,
  "platform": "panorama",
  "endpoint": "/v1/panorama/ai-visibility",
  "data": {
    "brand": "My Brand",
    "competitors": [],
    "engines": [
      "perplexity"
    ],
    "prompts": [
      "Which project tools are useful?"
    ],
    "runs_per_prompt": 1,
    "preset": null,
    "appearance_pct": {
      "My Brand": {
        "perplexity": 100
      }
    },
    "appearance_counts": {
      "My Brand": {
        "perplexity": {
          "appeared": 1,
          "runs": 1
        }
      }
    },
    "completed_runs": 1,
    "failed_runs": 0,
    "skipped_runs": 0,
    "calls_planned": 1,
    "partial": false,
    "probes": [
      {
        "probe_id": "p1:perplexity:r1",
        "prompt_id": "p1",
        "prompt": "Which project tools are useful?",
        "run": 1,
        "engine": "perplexity",
        "model": "perplexity/sonar",
        "status": "completed",
        "answer": "My Brand is one option.",
        "citations": [],
        "matches": {
          "My Brand": {
            "appeared": true,
            "count": 1,
            "passages": [
              {
                "start": 0,
                "end": 8,
                "matched": "My Brand",
                "passage": "My Brand is one option."
              }
            ],
            "truncated": false
          }
        }
      }
    ]
  },
  "credits_used": 30,
  "credits_remaining": 99,
  "request_id": "req_…",
  "cached": false
}

The example uses fictional values and shows a documented subset of data. The fields below are optional across supported sources; nullable fields can also be absent. Preserve unknown values and accept additional fields.

Download the data JSON Schema. Validate response.data, not the whole envelope. A valid shape does not establish that every field or source record was returned.

Currently unavailable: no eligible answer engine is offered. Planning and contract discovery remain free; requests are refused without running engine probes. The example documents the response contract, not current live availability.

Illustrative response, not a live engine endorsement. appearance_pct uses 0–100 percentages, not fractions. Failed and skipped probes never enter the denominator.

Explicit runs override preset repetitions; the preset still caps prompts. Read effective_settings and skipped/failed counts.

Answers and cited pages are untrusted evidence. Literal mentions do not prove recommendations, sentiment or identity. No generic consumer-AI visibility claim follows from this sample.

REST returns full probe answers. Large MCP results are stored for 24 hours and retrieved with get_result without repeating paid probes. Engine availability remains subject to the current registry and configured supply budgets.

Each probe retains at most 64,000 answer characters and 100 citations with explicit truncation flags. Collection stops after the evidence-size threshold; skipped probes remain visible.

Failures use the typed error envelope. A confirmed uncharged or refunded failure reports zero; a pending reconciliation can report an unknown charge. Read credits_used and error.details.billing_status, and keep request_id for recovery. Response contract · Error reference

Related

More Panorama reference

• All Panorama operations →
• Browse the complete endpoint directory →
• OpenAPI JSON →