Skip to content
Eden Engine

Text Sentiment & Aspect Analysis

omnial/x402-sentiment-analyze

Given a piece of text (a review, a comment, feedback), returns an overall sentiment label with confidence and a positive/negative/neutral score breakdown, plus aspect-level sentiment for individual topics mentioned in the text (e.g. product quality vs. customer service) with the exact text span that supports each one.

activeper callv1
Provider
Web & Business Data Network
Category
text-analysis
Provider price
$0.081082365 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": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to analyze"
    }
  },
  "additionalProperties": false
}
output_schema.json
{
  "type": "object",
  "properties": {
    "scores": {
      "type": "object",
      "properties": {
        "neutral": {
          "type": "number"
        },
        "negative": {
          "type": "number"
        },
        "positive": {
          "type": "number"
        }
      },
      "description": "Positive/negative/neutral breakdown, observed summing to 1 on both calls.",
      "additionalProperties": true
    },
    "aspects": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "aspect": {
            "type": "string",
            "description": "Short topic label, e.g. 'food quality'."
          },
          "sentiment": {
            "type": "string",
            "description": "This aspect's own sentiment label."
          },
          "text_span": {
            "type": "string",
            "description": "The exact substring of the input text that supports this aspect."
          }
        },
        "additionalProperties": true
      },
      "description": "One entry per distinct topic the text discusses (2 entries on the product review, 3 on the mixed restaurant feedback) -- not a fixed count."
    },
    "summary": {
      "type": "string",
      "description": "A one-to-two sentence plain-language summary of the analysis."
    },
    "sentiment": {
      "type": "string",
      "description": "Overall label observed as 'positive' and 'mixed' across the two real calibration calls; the endpoint's own description also documents 'negative' and 'neutral' as possible values, neither observed yet."
    },
    "confidence": {
      "type": "number",
      "description": "0-1. 0.98 on an unambiguous positive review, 0.92 on a mixed one."
    },
    "detected_language": {
      "type": "string",
      "description": "e.g. 'English'. Observed as a full language name, not an ISO code."
    }
  },
  "description": "The sentiment record, 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
$0.081082365
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