# GlianaAI Face Embed

> GlianaAI Face Embed is a paid API for AI agents from gliana-ai.glianalabs.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Generates a 512-dimensional face embedding vector from an image for use in face recognition and similarity tasks

## Facts

- Endpoint: GET https://gliana-ai.glianalabs.workers.dev/x402/tools/face-embed
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/glianaai-face-embed-95da893c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oYT-lOvKmoUAuUmzIBCkF

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 glianaai-face-embed-95da893c
```

Example prompt: Generate a 512-dimensional face embedding for the person in this photo: https://example.com/portrait.jpg — I need the vector to compare against other faces in my database.

## When to prefer this

Use this endpoint when you need to generate a face embedding vector from a single image for downstream tasks like face verification, similarity search, or clustering. Prefer this over face-compare when you want to store or reuse the raw embedding rather than compute a one-shot similarity score. Well-suited for pay-per-call use cases with no signup overhead, paying in USDC via x402.

## Known failure modes

- No face detected in the image — returns empty or error response
- Image URL is inaccessible or returns non-image content
- base64 payload is too large — recommended to use upload flow via /v1/media for large images
- Payment not received or USDC balance insufficient — 402 Payment Required
- Invalid image format or corrupted image data
- Multiple faces in image — may return multiple vectors or only the most prominent face

## How this service works

tools/face-embed: utility API on GlianaAI - pay-per-call, no signup, USDC. Input: { image_url | image_base64 }. Upload flow: POST raw image to /v1/media -> { url } -> pass as image_url. Returns one 512-d vector per face. base64 only for small images. https://ai.glianalabs.com

## Output

Returns one 512-dimensional floating-point vector per detected face in the provided image, suitable for use in similarity search, clustering, or face verification pipelines.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "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/glianaai-face-embed-95da893c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from gliana-ai.glianalabs.workers.dev](https://www.zero.xyz/host/gliana-ai.glianalabs.workers.dev/llms.txt)