# Delx P95 Estimate

> Delx P95 Estimate is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-13).

Estimates the 95th percentile (p95) latency from a bounded numeric sample array, returning a deterministic JSON result.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/p95-estimate
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-p95-estimate-033a2290
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_A5m-zO3CUgooEgiGCj10A

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-p95-estimate-033a2290 -d '<json body>'
```

Example prompt: Estimate the p95 latency from these response time samples in milliseconds: [120, 135, 98, 210, 87, 305, 142, 119, 201, 95, 178, 250].

## When to prefer this

Choose this endpoint when you need a fast, cheap, deterministic p95 latency estimate from a sample array with no external dependencies. Ideal for SRE agents, ops dashboards, and SLA-checking pipelines that need tail latency quantification at scale without paying for heavyweight analytics infrastructure. At $0.003 per call it is cost-effective for high-frequency monitoring loops. Prefer this over general-purpose statistics libraries when you want a zero-setup, stateless HTTP computation with a consistent JSON response contract.

## Known failure modes

- Empty or missing samples array — likely returns an error or null result
- Non-numeric values in the samples array — may cause computation failure or be silently ignored
- Insufficient sample size — may produce statistically unreliable p95 estimate
- Payment failure via x402 — request blocked if $0.003 USDC transaction cannot be completed
- Malformed JSON input — 400-level error returned

## How this service works

Estimate p95 latency from a bounded numeric sample — call when estimating p95 from a bounded numeric sample. Use for SRE/ops math agents buy from broad utility catalogs: SLA, error budget, success rate, and health scores with zero upstream cost. Returns deterministic machine-readable JSON for $0.003 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, and no claim of live chain tip, web search, or media generation. Re…

## Output

Returns a deterministic JSON object containing the estimated p95 (95th percentile) value derived from the provided numeric sample array. The response is machine-readable and stateless, with no upstream dependencies.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "samples": {
   "type": "array",
   "description": "Latency or metric samples for quantile estimation."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "max": 200,
  "min": 10,
  "p95": 200,
  "count": 11,
  "schema": "delx/util-p95-estimate/v1",
  "advisory": "Order-statistic estimate on the provided sample only."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-p95-estimate-033a2290/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)