API Documentation

Integrate Vizion computer vision models into your application.

Authentication

All API requests require a Bearer token. Create an API key in your dashboard.

Authorization: Bearer vz_live_your_api_key_here

Available Models

Model ID	Name	Description	Credits
sam3	SAM-3	Segment Anything Model 3 — state-of-the-art image segmentation	5
yolo	YOLO	Real-time object detection with high accuracy	2
depth-anything-3	DepthAnything 3	Monocular depth estimation for any image	3

Inference Endpoint

POST /api/v1/inference

Validates your API key, deducts credits, and authorizes the inference request. The GPU inference server calls this endpoint before processing.

Request

curl -X POST https://www.vizion.fast/api/v1/inference \
  -H "Authorization: Bearer vz_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"model": "yolo"}'

Success Response (200)

{
  "authorized": true,
  "model": "yolo",
  "credits_deducted": 2
}

Insufficient Credits (402)

{
  "error": "Insufficient credits",
  "credits_required": 2
}

Invalid Key (401)

{
  "error": "Invalid API key"
}

List Models

GET /api/v1/models

Returns available models with their credit costs. No authentication required.

curl https://www.vizion.fast/api/v1/models

Credit Costs

Each API request consumes credits based on the model used:

SAM-3 (sam3) — 5 credits per request
YOLO (yolo) — 2 credits per request
DepthAnything 3 (depth-anything-3) — 3 credits per request