# Foundry Sentiment Analysis

> Foundry Sentiment Analysis is a paid API for AI agents from minty-sprout.onrender.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-11-01).

Classifies text as positive, negative, neutral, or mixed sentiment with a numeric score from -1 to 1 and a confidence value.

## Facts

- Endpoint: POST https://minty-sprout.onrender.com/v1/sentiment?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/foundry-sentiment-analysis-219a7b7a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hV-k8dTzkj_pISzqHmN28

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 foundry-sentiment-analysis-219a7b7a -d '<json body>'
```

Example prompt: Can you analyze the sentiment of this customer review and tell me whether it's positive, negative, neutral, or mixed, along with a score and confidence level: 'The product arrived on time but the packaging was completely crushed and customer support never responded.'

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-call sentiment classifier that returns a numeric score alongside a discrete label and confidence value, without requiring API key setup or subscriptions. It is well-suited for agents processing one piece of text at a time — reviews, support tickets, social posts — especially in x402-compatible payment workflows where cost transparency per call matters.

## Known failure modes

- Text exceeding 8000 characters may be rejected or truncated
- Empty or whitespace-only input may return a null or undefined sentiment
- Ambiguous or very short text may produce low confidence scores
- Non-English text may yield less accurate sentiment classification
- Network or service unavailability on the Render.com host may cause 5xx errors

## How this service works

Sentiment analysis: positive, negative, neutral or mixed, with a score from -1 to 1. Input: any text.

## Output

A JSON object containing the input character count, a sentiment label (positive, negative, neutral, or mixed), a numeric score between -1 (most negative) and 1 (most positive), and a confidence value between 0 and 1 indicating how certain the model is about the classification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "maxLength": 8000,
   "description": "Any text up to 3,000 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "chars": 28,
  "score": 0.9,
  "sentiment": "positive",
  "confidence": 0.95
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/foundry-sentiment-analysis-219a7b7a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from minty-sprout.onrender.com](https://www.zero.xyz/host/minty-sprout.onrender.com/llms.txt)