# JarvisClaw Moderations API

> JarvisClaw Moderations API is a paid API for AI agents from uat.jarvisclaw.ai, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-15).

Runs content moderation on text input to detect harmful, unsafe, or policy-violating content, routed through an OpenAI-compatible AI gateway with pay-per-call USDC billing.

## Facts

- Endpoint: GET https://uat.jarvisclaw.ai/v1/moderations
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/jarvisclaw-moderations-api-7237d77d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_NwPyG9a7Q7fLriwc6UAOZ

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 jarvisclaw-moderations-api-7237d77d
```

Example prompt: Can you check whether this user comment is safe to post? The text is: 'You should go hurt yourself and everyone around you.' Flag any harmful categories it might fall under.

## When to prefer this

Choose this endpoint when you need a pay-per-call content moderation solution with no subscription commitment, compatible with the OpenAI moderation API format, and settled in USDC on Base or Solana. Ideal for agents operating in crypto-native or x402-payment environments where traditional API key billing is not preferred.

## Known failure modes

- Empty or missing input field returns a validation error
- Overly long input strings may be truncated or rejected
- Network or gateway routing errors may return 5xx responses
- Payment failure (insufficient USDC balance) blocks the call with a 402 response
- Ambiguous or borderline content may produce inconsistent flagging across calls

## How this service works

AI API Gateway with smart routing, pay per call via x402. OpenAI-compatible. Settled in USDC on Base & Solana.

## Output

Returns a moderation object indicating whether the input text was flagged, along with category-level breakdowns (e.g. hate, violence, self-harm, sexual content) and associated confidence scores, following OpenAI's moderation response format.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "Request input"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/jarvisclaw-moderations-api-7237d77d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from uat.jarvisclaw.ai](https://www.zero.xyz/host/uat.jarvisclaw.ai/llms.txt)