agent-compression-biz-production.up.railway.app LIVE ON-CHAIN Base N/A Detect prompt injection and jailbreaks. Scan untrusted user input for attempts to manipulate an AI agent — instruction overrides, system-prompt extraction, jailbreaks, data exfiltration, tool abuse — before your agent acts on it. A security guardrail for LLM and agent pipelines.
Last updated 4m ago
Overview Protocol x402
Payment asset USDC
Network base
Category llm-inference
Source agentic-market
Health Status Operational
Uptime (window) 100%
Success rate —
Confidence 87%
Quotes (14d) 21
Last checked 6/27/2026, 1:05:38 AM
Latest x402 transactions On-chain USDC settlements received on Base · 0x22DE39071D40FbfdC0962c34c593fb863DA75dF6
Trust score is global for the provider. Latency, price and uptime are measured per endpoint (last 24h). Click a column to sort.
Sort Uptime▼ Latency↕ Price↕
▸ POST /v1/scrapeN/A
Scrape structured data from any web page. Give a URL and the fields you want; get clean structured JSON back. Turn websites into structured records — prices, titles, contacts, listings, specs — for sandboxed agents that can't browse. $0.04 · 235 ms · Base ▸ POST /v1/entitiesN/A
Named-entity recognition (NER). Extract people, organizations, locations, dates and monetary amounts from text into structured JSON. Identify entities for knowledge graphs and data enrichment. $0.03 · 152 ms · Base
▸ POST /v1/fetchN/A
Fetch and read any web page. Give a URL, get back the main content as clean Markdown or plaintext with nav/ads/boilerplate removed. Web access and browsing for sandboxed agents that can't reach the internet. Scrape a URL to LLM-ready text. $0.03 · 153 ms · Base ▸ POST /v1/classifyN/A
Classify and categorize text. Assign input to one of your supplied labels with a confidence score. Zero-shot text classification for routing, tagging, intent detection and triage. $0.02 · 311 ms · Base ▸ POST /v1/compressN/A
Compress and minimize LLM context. Turn verbose, messy, unstructured text into a dense token-minimal JSON object that keeps every fact. Reduce token usage, shrink prompts, and cut context costs for AI agents. $0.02 · 340 ms · Base ▸ POST /v1/detect-injectionN/A
Detect prompt injection and jailbreaks. Scan untrusted user input for attempts to manipulate an AI agent — instruction overrides, system-prompt extraction, jailbreaks, data exfiltration, tool abuse — before your agent acts on it. A security guardrail for LLM and agent pipelines. $0.02 · 592 ms · Base ▸ POST /v1/markdownN/A
Convert HTML to Markdown. Turn web pages, HTML or messy text into clean, well-structured Markdown (headings, lists, links, tables). Make web content LLM-ready. $0.02 · 155 ms · Base ▸ POST /v1/redactN/A
Detect and redact PII from text. Mask emails, phone numbers, names, addresses and government/card IDs with typed placeholders. Anonymize and sanitize data for privacy and compliance. $0.02 · 153 ms · Base ▸ POST /v1/rewriteN/A
Rewrite and rephrase text in a target style or tone (formal, casual, concise, friendly, professional). Paraphrase, adjust voice, and polish copy while preserving meaning. $0.02 · 152 ms · Base ▸ POST /v1/summarizeN/A
Summarize documents and long text. Produce a dense, accurate summary at a target length (short, medium, long). Condense articles, reports, transcripts and web pages for fast downstream reasoning. $0.02 · 454 ms · Base ▸ POST /v1/translateN/A
Translate text between languages. Convert content into any target language while preserving meaning, tone and formatting. Machine translation for multilingual agents and pipelines. $0.02 · 153 ms · Base ▸ POST /v1/cleanN/A
Clean and denoise text. Strip HTML tags, navigation, ads, cookie banners and boilerplate, returning only the meaningful human-readable plaintext. Prep scraped or messy content for an LLM. $0.01 · 253 ms · Base ▸ POST /v1/detect-languageN/A
Detect the language of text. Return the language name, ISO 639-1 code and a confidence score. Language identification for routing and multilingual pipelines. $0.01 · 184 ms · Base ▸ POST /v1/json-repairN/A
Repair broken JSON. Fix malformed, truncated or loosely-formatted JSON (single quotes, trailing commas, cut-off output) into valid parseable JSON. Recover LLM output that failed to parse. $0.01 · 152 ms · Base ▸ POST /v1/keywordsN/A
Extract keywords, tags and key phrases from text. Identify the most important terms and topics for indexing, tagging, SEO and search. Keyword and keyphrase extraction. $0.01 · 154 ms · Base ▸ POST /v1/moderateN/A
Moderate content for safety. Flag unsafe text by category (hate, harassment, violence, sexual, self-harm, illegal). Content moderation and safety filtering for user input and generated text. $0.01 · 336 ms · Base ▸ POST /v1/sentimentN/A
Analyze sentiment and emotion in text. Return a positive/negative/neutral label plus a -1..1 score. Gauge customer feedback, reviews, social posts and support messages. $0.01 · 216 ms · Base Same category, ranked by Trust score — switch to a more reliable or cheaper source.
