x402 AI Tools

unreachable

AI tools for agents, paid per call in USDC on Base and backed by AWS managed AI: OCR for images and PDFs (Textract), image labels, scene text, content moderation (Rekognition), language detection, sentiment, entities, key phrases and PII redaction (Comprehend), translation between 75 languages (Translate) and text to speech (Polly). Inputs that cannot be fetched or read are not charged.

AIBasex402 v2exactai.kagurazaka.dev ↗︎
Transactions · 30d
0
Volume · 30d
$0.00
Unique buyers · 30d
0
Uptime · 30d
48.6%
Latency p50
48ms
Reported calls · 30d
86

Endpoints (24 live)

  • POST /v1/image-text — Detects words and lines of text in a photo or screenshot (JPEG or PNG at a URL) with Amazon Rekognition, up to 100 words. Suited to signs, product labels and UI text; for documents use /v1/ocr. (0.003 USDC on Base)
  • POST /v1/speech — Turns text into speech with Amazon Polly and returns a signed URL of the audio, valid for an hour. Up to 3000 characters with standard voices or 1000 with neural ones. Voices include Joanna, Matthew (English), Mizuki, Takumi (Japanese), Lucia (Spanish), Lea (French), Vicki (German) and about 60 more. (0.02 USDC on Base)
  • POST /v1/pii — Finds personally identifiable information (names, addresses, emails, phone numbers, credit card and bank numbers, SSNs, passwords, IP addresses and more) in English or Spanish text with Amazon Comprehend. Returns each entity's type, offsets and score, and the text with each one replaced by [TYPE]. (0.008 USDC on Base)
  • POST /v1/language — Detects the dominant language of a text (over 100 languages) with Amazon Comprehend, from its first 1000 characters. Returns the most likely language codes with scores. (0.002 USDC on Base)
  • POST /v1/labels — Detects objects, scenes, activities and concepts in a JPEG or PNG at a URL with Amazon Rekognition. Returns labels with confidence, their categories and parent labels, and how many instances were located. (0.003 USDC on Base)
  • POST /v1/entities — Finds named entities (person, location, organization, commercial item, event, date, quantity, title, other) in a text with Amazon Comprehend, with their offsets and scores. Supports en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW; the language is detected when not given. (0.008 USDC on Base)
  • POST /v1/key-phrases — Extracts the key noun phrases of a text with Amazon Comprehend, with their offsets and scores. Supports en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW; the language is detected when not given. (0.008 USDC on Base)
  • POST /v1/translate — Translates up to 1500 characters with Amazon Translate between any of its 75 languages, detecting the source language when not given. Optional formal or informal tone for the languages that support it. (0.03 USDC on Base)
  • POST /v1/sentiment — Classifies the sentiment of a text with Amazon Comprehend and returns the score of each class. Supports en, es, fr, de, it, pt, ar, hi, ja, ko, zh, zh-TW; the language is detected when not given. (0.008 USDC on Base)
  • POST /v1/moderation — Detects explicit, suggestive, violent, drug, hate and other unsafe content in a JPEG or PNG at a URL with Amazon Rekognition. Returns safe (no label at or above min_confidence) and the labels found. (0.003 USDC on Base)
  • POST /v1/ocr — Reads printed and handwritten text from a JPEG, PNG, TIFF or single-page PDF at a URL with Amazon Textract. Returns the full text and every line with its confidence and position. (0.005 USDC on Base)
  • POST /v1/faces — Finds up to 100 faces in a JPEG or PNG at a URL with Amazon Rekognition and describes each: position, estimated age range, emotions, smile, glasses, beard, eyes and mouth open, pose and image quality. It does not identify anyone or compare faces. (0.003 USDC on Base)
  • GET /v1/faces (free)
  • GET /v1/pii (free)
  • GET /v1/labels (free)
  • GET /v1/language (free)
  • GET /v1/ocr (free)
  • GET /v1/sentiment (free)
  • GET /v1/entities (free)
  • GET /v1/speech (free)

+4 more endpoints.

First seen · last seen