# Delx Latency Summary

> Delx Latency Summary is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Computes p50, p95, p99, mean, min, and max latency statistics from an array of millisecond samples

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/latency-summary
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-latency-summary-738020e8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UYezJkyrJn-DxY67PEoWi

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 delx-latency-summary-738020e8 -d '<json body>'
```

Example prompt: Can you compute the p50, p95, and p99 latency summary for these response times in milliseconds: [120, 135, 98, 200, 310, 145, 88, 175, 420, 102]?

## When to prefer this

Choose this endpoint when you need fast, deterministic, local latency percentile computation (p50/p95/p99) without any third-party data dependency. Ideal as a preflight check in autonomous workflows before retrying requests, changing API behavior, or evaluating production reliability. Prefer it over rolling your own stats logic when you need structured, machine-readable output at minimal cost ($0.002 USDC) with guaranteed no upstream calls and no state side effects.

## Known failure modes

- Array contains fewer than 1 item — validation error returned, not billed
- Array exceeds 10,000 items — validation error returned
- Non-numeric or negative values in the array — schema validation failure
- Malformed JSON body — 400-class error
- Payment not provided or insufficient — 402 response via x402 protocol

## How this service works

Calculate p50, p95, p99, mean, min, and max from bounded latency samples. Use it before an autonomous workflow acts on untrusted input, changes an API, retries a request, or evaluates production reliability. Returns bounded machine-readable JSON for $0.002 USDC via x402 on Base. Execution is deterministic, first-party, local-only, stateless, and does not call an upstream provider; structured validation failures are not billed.

## Output

Returns a machine-readable JSON object containing p50, p95, p99, mean, min, and max computed from the submitted latency array; computation is deterministic and local with no upstream calls. Structured validation failures are returned without charge.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "latencies_ms": {
   "type": "array",
   "items": {
    "type": "number",
    "minimum": 0
   },
   "maxItems": 10000,
   "minItems": 1
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 5,
  "max_ms": 55,
  "min_ms": 12,
  "p50_ms": 22,
  "p95_ms": 50.2,
  "p99_ms": 54.04,
  "schema": "delx/latency-summary/v1",
  "mean_ms": 27.6
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-latency-summary-738020e8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)