# Silicon DNA Classifier

> Silicon DNA Classifier is a paid API for AI agents from rtt.phoenix-ai.work, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Classifies a client as HUMAN, LEGIT_AGENT, or MALICIOUS_BOT by analyzing IP address, HTTP headers, TLS fingerprint, timing jitter, behavioral entropy, and NIC fingerprinting.

## Facts

- Endpoint: GET https://rtt.phoenix-ai.work/api/v1/classify?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/silicon-dna-classifier-a93b3f06
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_51LfY0Qlrv7Pnn2P04WTj

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 silicon-dna-classifier-a93b3f06
```

Example prompt: Classify this incoming request for me — the client IP is 203.0.113.42 and here are the HTTP headers they sent — I want to know if it's a real human, a legitimate AI agent, or a malicious bot based on its TLS fingerprint and behavioral signals.

## When to prefer this

Choose this endpoint when you need real-time, network-layer bot/human/agent classification that goes beyond user-agent string inspection — particularly when you want TLS fingerprint, timing jitter, and NIC-level signals factored into the decision. Best suited for access-gating, fraud prevention pipelines, or traffic routing where distinguishing legitimate AI agents from malicious bots is critical.

## Known failure modes

- Missing or malformed IP address returns a validation error
- Empty or incomplete headers object may reduce classification accuracy or return an error
- Ambiguous or spoofed signals may result in low-confidence classifications
- Service unavailability returns a non-200 status; agents should implement retry logic
- VPN or proxy-masked IPs may reduce classification reliability

## How this service works

Silicon DNA agent identity classification. Behavioral timing analysis: CPU jitter entropy (L0), Shannon entropy (L2), Spearman rank correlation (L3) to classify as HUMAN, LEGIT_AGENT, MALICIOUS_BOT, SYBIL, or UNKNOWN (no evidence either way). Per paper Section 5.1. (GET variant: parameters in the query string.)

## Output

Returns a classification label — one of HUMAN, LEGIT_AGENT, or MALICIOUS_BOT — derived from multi-signal analysis of the submitted IP address and HTTP headers, including TLS fingerprint characteristics, timing jitter, behavioral entropy, and physical-layer NIC fingerprinting data.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "target": {
       "type": "string",
       "description": "Optional label echoed to the classifier"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/silicon-dna-classifier-a93b3f06/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from rtt.phoenix-ai.work](https://www.zero.xyz/host/rtt.phoenix-ai.work/llms.txt)