Analyze an image for captions, tags, objects, and readable text.
API ID
azure-vision-analyzeOverview
- Input
- An image and selected analysis features.
- Output
- Structured results for the features that were executed.
- Providers
- Azure AI Services
- Latest operational check
- Healthy
- API compatibility
- Primex Vision Analysis API
Recommended for
- Image understanding
- Visual metadata extraction
Supported features
- Captions
- Tags
- Objects
- OCR
Make your first request
View full setup# Requires curl and jq.
set -euo pipefail
API_KEY="YOUR_API_KEY"
GATEWAY='https://gateway.primexos.com'
FILE_PATH='image.png'
CONTENT_TYPE='image/png'
BYTE_SIZE=$(wc -c < "$FILE_PATH" | tr -d '[:space:]')
AUTHORIZATION=$(curl --fail-with-body -sS "$GATEWAY/v1/primex/files/upload-authorizations" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d "{\"purpose\":\"VISION_INPUT\",\"content_type\":\"$CONTENT_TYPE\",\"byte_size\":$BYTE_SIZE}")
UPLOAD_URL=$(printf '%s' "$AUTHORIZATION" | jq -r '.upload_url')
UPLOAD_METHOD=$(printf '%s' "$AUTHORIZATION" | jq -r '.method')
BLOB_TYPE=$(printf '%s' "$AUTHORIZATION" | jq -r '.headers["x-ms-blob-type"]')
UPLOAD_CONTENT_TYPE=$(printf '%s' "$AUTHORIZATION" | jq -r '.headers["Content-Type"]')
FILE_ID=$(printf '%s' "$AUTHORIZATION" | jq -r '.file_id')
curl --fail-with-body -sS -X "$UPLOAD_METHOD" "$UPLOAD_URL" \
-H "x-ms-blob-type: $BLOB_TYPE" \
-H "Content-Type: $UPLOAD_CONTENT_TYPE" \
--data-binary "@$FILE_PATH"
FINALIZED=$(curl --fail-with-body -sS -X POST "$GATEWAY/v1/primex/files/$FILE_ID/finalize" \
-H "Authorization: Bearer $API_KEY")
FILE_ID=$(printf '%s' "$FINALIZED" | jq -r '.file_id')
SERVICE_PAYLOAD='{"model":"azure-vision-analyze","file_id":"__PRIMEX_PRODUCTION_FILE_ID__","features":["read"]}'
SERVICE_PAYLOAD=$(printf '%s' "$SERVICE_PAYLOAD" | jq --arg file_id "$FILE_ID" 'walk(if type == "object" and .file_id? == "__PRIMEX_PRODUCTION_FILE_ID__" then .file_id = $file_id else . end)')
curl --fail-with-body "$GATEWAY/v1/vision/analyze" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d "$SERVICE_PAYLOAD"Executing this request uses your account’s API credits.
Sample input → output
Inputphoto.jpg + selected features
→Output preview
- caption
- Generated image caption
- tags
- Detected visual tags
- text
- Readable text when requested
Simplified preview based on the published service response contract.
Input requirements
Supported formats
JPEGPNGGIFBMP