L402 Detect Objects API

L402 API

Pay with Bitcoin, get AI results. Copy-paste the commands below.

Back to all services & pricing

Before You Start

Lightning Wallet

Phoenix, Muun, Wallet of Satoshi, Alby, or any LN wallet. Agents: CLW

Terminal or Tool

A command line, Postman, or lnget (recommended)

Private & No Signup

No account, no subscription, no personal data. Pay only when you use it

Want to try this without a terminal? Use Object Detection on the web — pay with any Lightning wallet, no setup needed.

Object Detection via L402

Detect and locate objects in images by name. Describe what to find in natural language and get bounding box coordinates with confidence scores. Returns structured JSON that agents can act on directly.

API Endpoint: https://sats4ai.com/api/l402/detect-objects

Constraints

Image must be base64-encoded (with or without data: prefix)
query is required — comma-separated object names
Returns JSON with bounding boxes as [x1, y1, x2, y2] pixel coordinates
5 sats per image

Step 1: Initial Request (get Invoice)

Send your base64 image and query. You will receive a 402 Payment Required response with a Lightning invoice.

Request body:

{
  "image": "<base64-encoded-image>",
  "query": "cat, dog, person"
}

Example curl command:

curl -X POST https://sats4ai.com/api/l402/detect-objects \
-H "Content-Type: application/json" \
-d '{
  "image": "<base64-encoded-image>",
  "query": "cat, dog, person"
}' \
-i

Step 2: Pay the Lightning Invoice

Pay the invoice with any Lightning wallet. Save the preimage your wallet provides after payment.

Step 3: Re-send with Payment Proof

curl -X POST https://sats4ai.com/api/l402/detect-objects \
-H "Content-Type: application/json" \
-H "Authorization: L402 <YOUR_MACAROON>:<YOUR_PREIMAGE>" \
-d '{
  "image": "<base64-encoded-image>",
  "query": "cat, dog, person"
}'

Example response:

{
  "detections": [
    { "label": "cat", "confidence": 0.92, "bbox": [120, 45, 340, 280] },
    { "label": "person", "confidence": 0.87, "bbox": [400, 30, 550, 410] }
  ]
}

Easier: Use lnget

lnget handles the full L402 flow automatically.

IMAGE_B64=$(base64 -w0 photo.png)

lnget -X POST https://sats4ai.com/api/l402/detect-objects \
  --json "{\"image\":\"$IMAGE_B64\",\"query\":\"cat, dog, person\"}"

Python Example

import requests, base64

# Encode image
with open("photo.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

payload = {
    "image": image_b64,
    "query": "cat, dog, person",
    "box_threshold": 0.25,     # optional
    "text_threshold": 0.25     # optional
}

# Step 1 — get invoice
r = requests.post("https://sats4ai.com/api/l402/detect-objects",
    json=payload,
    headers={"Content-Type": "application/json"})

# Step 2 — pay invoice with your Lightning wallet, get preimage

# Step 3 — re-send with auth
r2 = requests.post("https://sats4ai.com/api/l402/detect-objects",
    json=payload,
    headers={
        "Content-Type": "application/json",
        "Authorization": "L402 <macaroon>:<preimage>"
    })
result = r2.json()
for det in result["detections"]:
    print(f"{det['label']}: {det['confidence']:.2f} at {det['bbox']}")

Request Parameters

`image`: string required

Base64-encoded image data.

`query`: string required

Comma-separated names of objects to detect (e.g. "cat, dog, person").

`box_threshold`: number (optional, default 0.25)

Confidence threshold for detection boxes (0-1). Lower = more detections, higher = fewer but more confident.

`text_threshold`: number (optional, default 0.25)

Confidence threshold for text-to-region matching (0-1).

Pricing

5 sats per image.

Use Cases

Count specific objects in images (inventory, wildlife surveys)
Locate elements for downstream cropping or masking
Quality assurance — verify expected objects are present
Agent workflows that need structured spatial data from images