Skip to content
Eden Engine

TikTok Ad Interactive Analysis (Retention/CTR Curve by Material ID)

omnial/tiktok-ads-get-ad-interactive-analysis

Given a TikTok ad's material ID, returns a per-second time series for a chosen engagement metric (viewer retention/remain, click-through rate, conversion rate, clicks, or conversions) over a lookback window in days, plus a percentile rank comparing the ad's performance to other ads. Useful for spotting where viewers drop off in a video or how an ad's click-through rate is trending.

activeper callv1
Provider
Web & Business Data Network
Category
tiktok
Provider price
$0.0020475 per call
Latency p50 / p95
— / —
Success rate
—
Verified
—

Provider list price; Omnial MCP charges provider cost plus a platform markup on top.

Contract

input_schema.json
{
  "type": "object",
  "required": [
    "material_id"
  ],
  "properties": {
    "cookie": {
      "type": "string",
      "description": "Optional session cookie, only needed to analyze a private/account-scoped ad you control. Leave empty for a public ad."
    },
    "material_id": {
      "type": "string",
      "description": "The TikTok ad's material ID, the same numeric ID shown for the ad in TikTok Ads Manager / Creative Center."
    },
    "metric_type": {
      "type": "string",
      "default": "remain",
      "description": "Which engagement metric to analyze: remain (viewer retention, the default), ctr (click-through rate), cvr (conversion rate), clicks, or conversion."
    },
    "period_type": {
      "type": "integer",
      "default": 180,
      "description": "Lookback window for the analysis, in days."
    }
  },
  "additionalProperties": false
}
output_schema.json
{
  "type": "object",
  "properties": {
    "keyframe": {
      "type": "object",
      "properties": {
        "msg": {
          "type": "string",
          "description": "'OK' on both real calls observed."
        },
        "code": {
          "type": "number",
          "description": "0 on both real calls observed (success)."
        },
        "data": {
          "type": "object",
          "properties": {
            "analysis": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "value": {
                    "type": "number",
                    "description": "The metric's value at that second (e.g. a retention fraction for remain, a click-through rate for ctr). Observed as 0 on both real calls."
                  },
                  "second": {
                    "type": "number",
                    "description": "Second offset from the video start."
                  }
                },
                "additionalProperties": true
              },
              "description": "One entry per second of the video, in order. Every value was 0 across both real calibration calls (an older/lower-traffic ad) -- a genuine flat curve for that ad, not an error; a higher-traffic ad is expected to show nonzero values here."
            },
            "duration": {
              "type": "number",
              "description": "Total video duration in seconds covered by `analysis` (60 on both real calls)."
            },
            "highlight": {
              "type": "array",
              "items": {},
              "description": "Notable highlighted seconds/segments in the curve. Empty on both real calls observed; the shape of a populated entry was not confirmed."
            }
          },
          "additionalProperties": true
        }
      },
      "description": "The per-second engagement time series for the chosen metric_type.",
      "additionalProperties": true
    },
    "percentile": {
      "type": "object",
      "properties": {
        "msg": {
          "type": "string",
          "description": "'OK' on both real calls observed."
        },
        "code": {
          "type": "number",
          "description": "0 on both real calls observed (success)."
        },
        "data": {
          "type": "object",
          "properties": {
            "ctr_percentile": {
              "type": "number",
              "description": "Percentile rank (0-1) for the ctr metric. Present when metric_type=ctr; observed 0.99."
            },
            "show_cnt_percentile": {
              "type": "number",
              "description": "Percentile rank (0-1) for the remain/retention metric. Present when metric_type=remain; observed 0.99."
            }
          },
          "description": "The percentile key name matches the metric requested -- observed as `show_cnt_percentile` for metric_type=remain and `ctr_percentile` for metric_type=ctr. The other metric_type values (cvr, clicks, conversion) were not captured and presumably use a differently-named key here.",
          "additionalProperties": true
        }
      },
      "description": "A percentile-rank benchmark for the chosen metric_type against other ads.",
      "additionalProperties": true
    }
  },
  "description": "The interactive-analysis document, as returned at routing.responseResultPath ($.output).",
  "additionalProperties": true
}

Pricing

Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.

Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.

ChargeRate
Per call
Flat, regardless of what comes back
$0.0020475
Cost basis
Not recorded

This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.

Updated
Sep 23, 2026