$ man logo-detect
/logo-detect(1)
NAME
logo-detect — brand logo detection / brand recognition in images
SYNOPSIS
POST https://x402.org/v1/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. Vision LLM. Returns brands with confidence, location, evidence (wordmark/logomark/lockup/color_scheme), element_type. Supports hint_brands.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| image_url | string | URL of the image to scan for brand logos, wordmarks, lockups, or other brand elements. | required |
| hint_brands | array | Optional list of brands the caller suspects may be present (max 30). | 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.org/v1/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 once claude mcp add x402 --command "npx x402-deployer-mcp" # then ask Claude Code: # "use the logo-detect tool to ..."
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 | Video thumbnail / video frame extractor. | $0.03 |
| audio-loudnorm | Audio loudness normalizer (EBU R128 LUFS). | $0.02 |
| csv-to-jsonl | CSV to JSON / CSV to JSONL converter / data pipeline preprocessor. | $0.02 |
| image-translate | Image translator: vision-OCR + Venice translate. | $0.02 |
| image-upscale | Image upscale / 2x upscaler / 4x upscaler / super-resolution / sharpen image / enlarge image without loss. | $0.02 |
| pdf-watermark | PDF watermark / image watermark / video watermark — text or image overlay on PDFs, PNG/JPG/GIF, or MP4/MOV/WEBM. | $0.02 |
| video-to-subtitles | SRT / VTT subtitle generator from video or audio. | $0.02 |
| video-trim | Video trimmer / video cutter / video clip tool. | $0.02 |
SEE ALSO