# ArcFace Identity Similarity

> Run ArcFace Identity Similarity by eval online or via API. from $0.00055833/sec, no setup.

**URL:** https://inference.sh/apps/eval/arcface
**Last updated:** 2026-03-28

---

ArcFace identity similarity — cosine similarity between face embeddings of two images

- app: `eval/arcface`
- maker: [eval](https://inference.sh/apps/eval.md)
- category: [other](https://inference.sh/apps/category/other.md)
- tasks: [evaluation](https://inference.sh/apps/tag/evaluation.md)
- price: from $0.00055833/sec
- runs via: api, javascript and python sdk, belt cli, mcp

## arcface API Guide

### About
arcface identity similarity — cosine similarity between face embeddings of two images

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3s9tvkd5 pinned
result = client.run({
        "app": "eval/arcface@3s9tvkd5",
        "input": {
            "source": "https://example.com/file.png",
            "target": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3s9tvkd5 pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "eval/arcface@3s9tvkd5",
        "input": {
            "source": "https://example.com/file.png",
            "target": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "eval/arcface@3s9tvkd5",
        "input": {
            "source": "https://example.com/file.png",
            "target": "https://example.com/file.png"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "eval/arcface@3s9tvkd5",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **source** (string) *required*: Source/reference face image
- **target** (string) *required*: Target image to compare identity against

#### Output
- **similarity** (number): Cosine similarity between face embeddings (-1 to 1)
- **source_face** (object): Source face detection info
- **source_face_detected** (boolean): Whether a face was detected in the source
- **target_face** (object): Target face detection info
- **target_face_detected** (boolean): Whether a face was detected in the target

## other other apps

- [Google Analytics](https://inference.sh/apps/google/analytics.md): from $0.00000277/sec
- [Google Search Console](https://inference.sh/apps/google/search-console.md): from $0.00000277/sec
- [HTTP Request](https://inference.sh/apps/infsh/http.md): from $0.00000277/sec
- [PickScore](https://inference.sh/apps/eval/pickscore.md): from $0.00055833/sec
- [Gmail](https://inference.sh/apps/google/gmail.md): from $0.00000277/sec

## faq

### how much does ArcFace Identity Similarity cost?

from $0.00055833/sec. you pay per run from your inference shell credits. no subscription is required.

### how do I run ArcFace Identity Similarity via api?

call eval/arcface with the javascript or python sdk, the rest api, or `belt app run eval/arcface` from a terminal. the api reference on this page lists every input.

### who makes ArcFace Identity Similarity?

ArcFace Identity Similarity is made by eval and runs on inference shell. every eval app is listed at https://inference.sh/apps/eval.

### can my agent use ArcFace Identity Similarity?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to ArcFace Identity Similarity?

other other apps on inference shell include Google Analytics, Google Search Console, HTTP Request, PickScore. they run through the same api, so switching is a one-line change.