# SafeVision Content Moderation Chat API

> SafeVision Content Moderation Chat API is a paid API for AI agents from x402-ai-peach.vercel.app, paid per call via x402, $0.075/call, status unknown (last checked 2026-09-14).

Analyzes chat messages through a safety-focused AI vision model to detect harmful, unsafe, or policy-violating content via x402 micropayments

## Facts

- Endpoint: POST https://x402-ai-peach.vercel.app/api/safevision
- Price: $0.075/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/safevision-content-moderation-chat-api-ac09c849
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_PX9m1HfsFEM1o9cNDqmyf

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 safevision-content-moderation-chat-api-ac09c849 -d '<json body>'
```

Example prompt: Can you screen this batch of user messages for unsafe or policy-violating content using the SafeVision moderation API — up to 512 tokens per response — and flag anything that looks harmful?

## When to prefer this

Choose this endpoint when you need pay-per-use AI-powered content safety analysis without a subscription commitment, especially when you want micropayment-based billing via x402/USDC. It is well-suited for sporadic or burst moderation workloads where cost-per-call pricing is preferable to flat-rate plans. Prefer this over general-purpose LLM APIs when the specific use case is content safety screening and you want a purpose-named 'SafeVision' model tuned for that task.

## Known failure modes

- Payment failure: 402 response if x402 micropayment of $0.075 USDC is not properly attached
- Invalid messages array: 400 error if required 'messages' field is missing or malformed
- Token limit exceeded: truncated or error response if max_tokens is set too low for the analysis
- Timeout: slow or failed response if content is very large and streaming is not enabled
- Unsupported content type: model may return generic response if input format is unexpected

## How this service works

Paid AI API endpoints via x402 micropayments

## Output

Returns a JSON object with a unique response ID and a choices array containing AI-generated safety analysis messages. Each choice includes a role-tagged message with content describing the moderation verdict or safety assessment of the input messages.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "messages"
 ],
 "properties": {
  "stream": {
   "type": "boolean",
   "description": "Stream response"
  },
  "messages": {
   "type": "array",
   "description": "Chat messages array"
  },
  "max_tokens": {
   "type": "integer",
   "description": "Max tokens"
  },
  "temperature": {
   "type": "number",
   "description": "Temperature"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "id": {
   "type": "string",
   "description": "Response ID"
  },
  "choices": {
   "type": "array",
   "items": {
    "type": "object",
    "properties": {
     "message": {
      "type": "object",
      "properties": {
       "role": {
        "type": "string"
       },
       "content": {
        "type": "string"
       }
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/safevision-content-moderation-chat-api-ac09c849/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-ai-peach.vercel.app](https://www.zero.xyz/host/x402-ai-peach.vercel.app/llms.txt)