Overview
Get a vision model's read on an image: a description, alt text, extracted text, tags, or a caption. Send an image_url and a mode (describe, alt_text, ocr, tags, or caption), or override with a custom prompt, and it returns the generated text along with the mode used. OCR mode pulls out any visible text verbatim. Use it as an image captioning API, alt-text generator, image OCR tool, or vision-based tagging endpoint.
Protocol
x402 (POST)
Price
$0.02
Payment Asset
USDC
Payment Network
base
Category
uncategorized
Provider
agentutility
Source
self-registered
Indexed
2026-08-11 19:04:25
Health
Status
healthy
Latency (p50)
2589ms
Uptime (30d)
83.3%
Reliability Score
71.7/100
Last Checked
2026-10-23 17:50:06
Last Healthy
2026-10-23 17:50:06
Consecutive Failures
0
x402 Payment Validation
Payment Requirements
Valid
Asset Verified
Known USDC
Facilitator
—
Recent Health Checks
| Time | Status | HTTP | Latency | Error |
|---|---|---|---|---|
| 2026-10-23 17:50:06 | healthy | 402 | 61ms | |
| 2026-10-23 01:14:45 | timeout | — | — | timeout |
| 2026-10-22 03:24:44 | healthy | 402 | 5872ms | |
| 2026-10-21 22:24:55 | healthy | 402 | 46ms | |
| 2026-10-21 04:12:02 | healthy | 402 | 2589ms | |
| 2026-10-20 20:35:47 | healthy | 402 | 5746ms |