# GG402 Sentiment Analysis

> GG402 Sentiment Analysis is a paid API for AI agents from gg402.vercel.app, paid per call via x402, $0.010000/call, status unknown (last checked 2026-09-15).

Analyzes the sentiment of a given text string, returning a numeric score, sentiment label, and natural language explanation.

## Facts

- Endpoint: POST https://gg402.vercel.app/sentiment
- Price: $0.010000/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gg402-vercel-app-3c85b3f8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WfkeFIEEGTM8yB-Yij_Ng

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability gg402-vercel-app-3c85b3f8 -d '<json body>'
```

Example prompt: Can you analyze the sentiment of this text and give me a score and explanation: 'The Fed's latest rate decision rattled investors, with markets closing sharply lower amid widespread uncertainty about future policy direction.'

## When to prefer this

Choose this endpoint when you need a fast, affordable ($0.01 USDC), single-call sentiment classification with a human-readable explanation — especially for financial text, news snippets, or social media content. Prefer it over heavyweight NLP pipelines when simplicity and speed matter more than batch throughput or fine-grained emotion categories.

## Known failure modes

- Missing 'text' field returns a validation error
- Empty string input may return an undefined or neutral result
- Extremely long text may be truncated or cause a timeout
- Non-English text may produce less accurate sentiment classification
- Ambiguous or sarcastic text may result in incorrect sentiment labeling

## How this service works

Real-time sentiment analysis of text, news, and social media to gauge market and community sentiment.

## Output

Returns the original text, the model used (gpt-4o-mini), a numeric sentiment score (0–1 scale), a sentiment label (e.g. 'positive', 'negative', 'neutral'), and a plain-English explanation of why the text received that sentiment rating.

## Example request

```json
{
 "text": "The new product launch exceeded expectations with strong customer feedback and positive market reception."
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text",
  "model",
  "score",
  "sentiment",
  "explanation"
 ],
 "properties": {
  "text": {
   "type": "string"
  },
  "model": {
   "type": "string"
  },
  "score": {
   "type": "number"
  },
  "sentiment": {
   "type": "string"
  },
  "explanation": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gg402-vercel-app-3c85b3f8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gg402.vercel.app](https://www.zero.xyz/host/gg402.vercel.app/llms.txt)