# PQS Batch Prompt Quality Scoring

> PQS Batch Prompt Quality Scoring is a paid API for AI agents from pqs.onchainintel.net, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-14).

Scores up to 10 prompts in a single API call across 8 quality dimensions, returning structured quality breakdowns and improvement suggestions for each.

## Facts

- Endpoint: GET https://pqs.onchainintel.net/api/score/batch
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pqs-onchainintel-net-0def59d8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YGKB31l1XVpSe-8e468e1

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 pqs-onchainintel-net-0def59d8
```

Example prompt: Score these 5 prompts for me using the 8-dimension PQS quality rubric and tell me which ones are worth sending to GPT-4 and which need fixing: [list of 5 prompts].

## When to prefer this

Use this endpoint when you need to evaluate multiple prompts at once and want to avoid the overhead of making separate scoring calls for each one. Ideal for agents that generate or collect batches of candidate prompts and need to efficiently filter or rank them before committing to expensive LLM calls. Prefer this over the single-prompt scoring endpoint whenever you have 2 or more prompts to evaluate.

## Known failure modes

- More than 10 prompts submitted — batch limit exceeded
- Empty prompts array — returns validation error
- Malformed request body — JSON parse error
- Payment not attached or insufficient — x402 payment required error
- Individual prompts too long — token/length limit exceeded per prompt

## How this service works

PQS batch scoring - score up to 10 prompts in one call

## Output

Returns a quality score and 8-dimensional breakdown for each submitted prompt, including framework-level analysis and top recommended fixes, allowing the agent to identify which prompts are strong enough to send to a paid LLM and which need improvement before use.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "prompts": {
   "type": "array",
   "items": {
    "oneOf": [
     {
      "type": "string",
      "maxLength": 10000,
      "minLength": 1
     },
     {
      "type": "object",
      "required": [
       "prompt"
      ],
      "properties": {
       "prompt": {
        "type": "string",
        "maxLength": 10000,
        "minLength": 1
       },
       "vertical": {
        "enum": [
         "software",
         "content",
         "business",
         "education",
         "science",
         "crypto",
         "general",
         "research"
        ],
        "type": "string"
       }
      }
     }
    ]
   },
   "maxItems": 10,
   "minItems": 1,
   "description": "Array of 1-10 prompts. Each item is a string or {prompt, vertical} object."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pqs-onchainintel-net-0def59d8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from pqs.onchainintel.net](https://www.zero.xyz/host/pqs.onchainintel.net/llms.txt)