# Andreax

> 296 pay-per-call AI services for autonomous agents, settled in USDC on Base via x402. No account, no API keys. Every service has a free preview with ?sample=1. Callable over HTTP (x402) or MCP.

- **Domain**: `pagos.andreax.dev`
- **Provider**: Andreax (https://pagos.andreax.dev/tienda)
- **A2A protocol version**: 0.3.0
- **Kind**: paid_api
- **Live-responds (last probe)**: True
- **Signed card**: False
- **Streaming**: False
- **Quality score**: 100%
- **Payment protocol**: x402 · network `eip155:8453` · ≥ $0.001
- **Wallet**: `0x1f699cd1ac91e7c0ba9abb2dd3c480fbd252a7f9`

## Skills
- **market-data** — Spot USDC/COP price and market depth (premium data). (0.001 USDC/call, x402)
- **ai-inference** — Model answer to your query (pay-per-use AI compute). (0.002 USDC/call, x402)
- **rwa-report** — Yield and risk of 12 tokenized RWA funds, updated. (0.005 USDC/call, x402)
- **compress** — Compress a prompt into dense language and return the version with fewer tokens (typical 20-40% saving). Use it BEFORE sending prompts to any LLM to cut token co
- **distilla-compress** — Distilla (branded, real PyPI package): compress a prompt to dense language, same meaning, fewer tokens. input=prompt to compress. (0.02 USDC/call, x402)
- **distilla-evocation-score** — Distilla: score how dense a prompt already is, 0-100 (higher = less filler to cut). input=prompt to score. (0.01 USDC/call, x402)
- **distilla-identity** — Distilla: generate 7 dense identity aphorisms for a system from its description. input=system description. (0.05 USDC/call, x402)
- **inference** — Return an LLM (Kimi/DeepSeek) answer to your query. General-purpose, pay-per-call inference for when an agent needs a model response. input=your query as text. 
- **fx** — Quote a currency conversion into USDC with spread (e.g. COP->USDC, USD->USDC). Get stablecoin exchange rates. input='<amount> <from> <to>'. (0.001 USDC/call, x4
- **research** — Research a topic on the web and return a synthesis with cited sources (titles + URLs). Pay-per-query research for when an agent needs current information with s
- **read-url** — Download a web page and return its clean, readable text (no HTML or scripts). Let an agent read a URL's content pay-per-call. input=http(s) URL. (0.002 USDC/cal
- **report** — Generate a written, structured research report on a topic: researches the web and synthesizes a 400-600 word report with cited sources. Premium service for when
- **crypto-price** — Return the LIVE price of a cryptocurrency in USD and COP with its 24h change (real market data). High volume for agents that need prices. input=symbol or id (bt
- **embeddings** — Turn text into a vector (embedding) for semantic search, RAG, clustering or memory. The building block every AI agent needs. High volume. input=text. (0.001 USD
- **semantic-search** — Rank a list of documents by MEANING closeness to a query (cosine similarity over embeddings). Ready-to-use RAG, no need for the agent to run its own vector DB. 
- **read-pdf** — Download a PDF from a URL and return its extracted text. Let an agent read documents (reports, contracts, papers) pay-per-call. input=http(s) URL of a PDF. (0.0
- **wallet-balance** — Return the on-chain balance (ETH and USDC) of an address on the Base network. Live on-chain read for agents verifying funds or balances. input=0x address. (0.00
- **ocr** — OCR: extract text from an image (JPG/PNG) or a PDF, including scanned PDFs with no text layer. Local engine (Tesseract 5), Spanish and English. Upload the file 
- **vision** — Computer vision: describe or analyze an image with a LOCAL multimodal model (llava). For agents that need to 'see' (describe scenes, read diagrams, classify ima
- **transcribe** — Transcribe an audio file to text (speech-to-text) with LOCAL Whisper, automatic language detection. For agents processing voice notes, calls or podcasts. Upload
- **smart-document** — Premium PIPELINE in a single call: takes an image or PDF, extracts its text (OCR), summarizes it and translates the summary to the target language. For agents t
- **meeting-minutes** — Premium PIPELINE in a single call: takes an audio (meeting, voice note, call), transcribes it with local Whisper and writes MINUTES with Summary, Decisions and 
- **deep-research-report** — PREMIUM: full research report with cited web sources. input=topic. (5.0 USDC/call, x402)
- **screen-aware-assist** — PREMIUM: reads your screen (VLM) and assists. input=question. (2.0 USDC/call, x402)
- **voice-clone-tts** — PREMIUM: returns SSML ready for your TTS engine. input=text. (3.0 USDC/call, x402)
- **predictive-analytics** — PREMIUM: trend + short-term prediction + risks over your data. input=data/series. (10.0 USDC/call, x402)
- **multi-agent-debate** — PREMIUM: multi-model debate (DeepSeek+Kimi) then a judged conclusion. input=question. (7.0 USDC/call, x402)
- **code-review-security** — PREMIUM: security-focused code review by severity. input=code. (4.0 USDC/call, x402)
- **market-intelligence** — PREMIUM: market intelligence with live data + scenarios. input=asset/market. (8.0 USDC/call, x402)
- **autonomous-workflow** — PREMIUM: executable step-by-step autonomous workflow plan. input=goal. (15.0 USDC/call, x402)
- **content-pipeline** — PREMIUM: full content pipeline (post + variants + hashtags). input=brief. (5.0 USDC/call, x402)
- **compliance-audit** — PREMIUM: compliance/legal-risk audit by severity. input=document/policy. (20.0 USDC/call, x402)
- **comprimir** — CONSUMER: compress a prompt to dense language keeping meaning (<=50%). input=text. B2B: save LLM tokens in pipelines. (0.001 USDC/call, x402)
- **contar-tokens** — CONSUMER: exact token count (tiktoken) for a model. input=text, modelo=optional. B2B: budget LLM calls. (0.001 USDC/call, x402)
- **interpretar** — CONSUMER: detect intent + categories + sentiment. input=message, categorias=optional. B2B: ticket routing, chatbots. (0.001 USDC/call, x402)
- **fast-translate** — CONSUMER: translate + proofread to any language. input=text, to=lang. (0.05 USDC/call, x402)
- **quick-summary** — CONSUMER: summary + keywords. input=text. (0.02 USDC/call, x402)
- **email-polish** — CONSUMER: rewrite email formal + proofread. input=draft, tono=optional. (0.05 USDC/call, x402)
- **doc-extract** — CONSUMER: extract structured JSON from a document. input=text, campos=optional. (0.1 USDC/call, x402)
- **audio-to-text** — CONSUMER: clean + summarize a transcript. input/transcript=text. (0.2 USDC/call, x402)
- **image-describe** — CONSUMER: describe image + entities. image=base64|url. (0.1 USDC/call, x402)
- **code-explain** — CONSUMER: explain code + basic improvements. input=code. (0.1 USDC/call, x402)
- **topic-classify** — CONSUMER: classify topic + entities. input=text, labels=optional. (0.02 USDC/call, x402)
- **language-detect** — CONSUMER: detect language (ISO code). input=text. (0.001 USDC/call, x402)
- **fact-check-quick** — CONSUMER: quick fact-check with web sources. input=claim. (0.1 USDC/call, x402)
- **seo-article** — SMB: keyword-researched long-form SEO article + meta tags. input=topic. (3.0 USDC/call, x402)
- **competitor-scan** — SMB: competitor research + SWOT + positioning + how-to-win. input=company. (5.0 USDC/call, x402)
- **lead-enrich** — SMB: enrich a B2B lead + outreach angle + subject line. input=domain/company. (2.0 USDC/call, x402)
- **social-calendar** — SMB: 14-day content calendar (posts+hashtags+times). input=brand, red=optional. (4.0 USDC/call, x402)
- **product-listing** — SMB: optimized ecommerce listing (title+bullets+desc+SEO). input=product data. (3.0 USDC/call, x402)

## URLs
- Agent card: https://pagos.andreax.dev/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/pagos.andreax.dev
- Documentation: https://andreax.dev/llms.txt