agentutility(7)$ man logo-detect
/logo-detect
NAME
logo-detect — brand logo detection / brand recognition in images
SYNOPSIS
POST https://x402.agentutility.ai/logo-detect
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Brand logo detection / brand recognition in images. Venice qwen3-5-9b vision LLM. Returns detected brands with confidence, location, evidence (wordmark/logomark/lockup/color_scheme), element_type, and supports hint_brands.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| image_url | string | Public http(s) image URL to scan for brand logos. | required |
| hint_brands | array | Optional. Up to 30 brand names to hint the detector; detections still require visual evidence. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| detected_brands | array | Array of detected brands with confidence score, bounding location, evidence type, and element_type per match. |
| overall_summary | string | Short natural-language summary of which brands were found in the image and where they appear. |
| no_brands_detected | boolean | True when the vision model found no recognizable brand logos or marks in the image. |
| image_url | string | Echoes back the input image URL that was analyzed for brand detection. |
| hint_brands | array | Echoes the optional list of brand names the caller passed as hints to bias detection toward. |
| model | string | Identifier of the vision LLM that produced the detection result. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/logo-detect \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# Install the MCP package for this endpoint's cluster npx -y @agentutility/mcp-<cluster> # Required: EVM private key with USDC on Base export X402_PRIVATE_KEY=0x... # Then call the logo-detect tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- brandlogovisiondetectimage
- env
- VENICE_API_KEY
- methods
- POST
- cluster
- mediakit
- price
- $0.03 USDC per call
ADJACENT — other endpoints in mediakit
| endpoint | description | price |
|---|---|---|
| video-thumbnail | Pull a single still frame out of a video without transcoding the whole file. | $0.03 |
| add-watermark | Stamp a text or image watermark onto a PDF, image, or video file. | $0.02 |
| audio-loudnorm | Normalize audio loudness to a target LUFS level for podcasts, YouTube, and Spotify delivery. | $0.02 |
| csv-to-jsonl | Converts CSV or TSV data into JSON, JSONL/NDJSON, or column-oriented arrays. | $0.02 |
| image-translate | Image translator. | $0.02 |
| image-upscale | Upscales an image 2x or 4x via Venice's image/upscale endpoint (default model: venice-sd35). | $0.02 |
| image-watermark | Image watermark / add text or logo watermark to image files. | $0.02 |
| mp4-to-mp3 | Converts MP4, MOV, WebM, MKV, AVI, M4V, and FLV video files to MP3 via CloudConvert, with selectable bitrate (96/128/192 kbps). | $0.02 |
SEE ALSO