Every agent-payable API.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

AI Document Search Preparation: Split up to 12000 characters of supplied plain text into overlapping chunks and produce MiniLM embeddings. Returns a portable search dataset; not a hosted database. Local processing. Limits and retention: /ai-services.

AI intent execution - natural language commands translated to API actions automatically

Automatically select a suitable open-weight model from Kimi K3, Qwen3.6-35B-A3B, and GLM-5.2, then generate a chat completion. The exact price is calculated from the selected model, prompt, and requested maximum completion tokens.

AI-powered code review. Returns bugs, improvements, and security issues.

AI-powered company research. Retrieves live public sources (Wikipedia, web abstracts, SEC EDGAR, company site) and returns a structured report: overview, key facts, financials when available, risks, opportunities and full source citations.

AI-powered sentiment analysis. Send text, get sentiment score + emotions. Paid via x402.

AI responses API - OpenAI-compatible multi-turn agent responses, pay per token with USDC

AI share of voice — compare 2-5 brands across ChatGPT, Gemini, Google AI Overviews, Google AI Mode, Perplexity and Claude. Returns % of queries where each brand is cited per engine. 1.50 USDC.

AI Structured Field Extraction: Extract up to five named fields from up to 1200 characters. Each value must be an exact source substring or null, with missing information left empty. Local processing. Limits and retention: /ai-services.

AI Structured Output Validation: Validate a JSON value against a documented schema subset: types, properties, required, items, enums and size/number limits. No external references or regex execution. Local processing. Limits and retention: /ai-services.

AI Text Classification: Classify up to 1200 characters into one of 2..6 customer labels. Returns a label and brief rationale; no calibrated confidence claim. Local processing. Limits and retention: /ai-services.

AI Text Embeddings: Generate normalized 384-dimensional MiniLM embeddings for up to 32 texts, each up to 1000 characters. Token truncation is reported. Local processing. Limits and retention: /ai-services.

AI Text Generation: general-purpose AI text generation for any prompt Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-llm-chat","request":"<input>"}. No account, no API key.

AI token verdict built on real on-chain checks: send a token contract address (Base, Ethereum, BSC, Arbitrum, Polygon) or a Solana mint and get everything from token-verdict (grade A to F, SAFE to DANGER label, 0 to 100 score, honeypot sell simulation, buy and sell tax, mint, freeze and owner powers, liquidity, shareable verdict card) plus an AI-written take for a trader: a headline, 3 to 4 plain sentences on what the grade means, red flags, green flags and which fact would change the grade.

Give a Base transaction hash and Claude explains what it actually did in plain English — the action, a risk read (failed tx, risky approval, high-value transfer), and notes. Turns raw calldata into an answer agents and humans can use.

Deterministic preflight check for a proposed AI agent action - a tool call, payment, fetch, or write - before it executes. Evaluates up to four independent checks (prompt-injection scan on action text/untrusted text, URL/hostname validation, a bounded JSON-schema check on a payload, and a spend proposal against a spend mandate) and returns ALLOW, REVIEW, or BLOCK with stable reason codes plus a SHA-256 request/receipt hash pair.

How ready a website is for AI agents: llms.txt, AI-crawler rules in robots.txt, sitemap, x402 payment discovery, OpenAPI, MCP manifest, security.txt, with a 0-100 score and concrete recommendations.

AI code review. Returns issues with severity, line numbers, fix suggestions. Focus on security, performance, readability, or bugs.

AI news brief for Finance: Find recent reporting about artificial intelligence AI. Focus: finance. Uses live Google News RSS results.

AI news brief for Product teams: Find recent reporting about artificial intelligence AI. Focus: product teams. Uses live Google News RSS results.

AI news brief for Small business: Find recent reporting about artificial intelligence AI. Focus: small business. Uses live Google News RSS results.

Current weather at a place: temperature (°C), humidity (%), pressure (hPa) and wind (m/s) from the nearest live Open-Meteo relay within 75 km, with a signed receipt. Send latitude and longitude, or a city.

The nearest live public sensors to a point, one per layer asked for (weather, air, radiation, quake …), each with its reading, distance and source, and a signed receipt.

Debug an x402 payment before you submit it — why does USDC answer invalid signature? Verifies the EIP-3009 transferWithAuthorization (EIP-712 signer, v, low s, validity window) and the seller's terms (payTo, amount, asset, network, bound nonce), and names the domain a failing signature was really made for, e.g. Base Sepolia's 'USDC' used for Base mainnet's 'USD Coin', the commonest reason an x402 payment reverts. Offline, deterministic, signed answer.

MCP security: catch a rug pull or tool poisoning between two tools/list results of the same MCP server — the version you approved and the one it serves now. Flags instructions aimed at the model, override and concealment wording, credential and wallet paths, covert actions, hidden Unicode, new URLs and addresses, a dropped readOnlyHint, new command or path parameters and look-alike tool names; verdict unchanged, changed, review or suspicious, with a word diff per changed tool.

WARDEN verdict on an MCP server's tools/list: allow or block, a 0-1 score and every finding with the matched text (prompt injection, secret requests, exfiltration, hidden Unicode). Deterministic published rules, no network.

HISTOR pre-flight for an MCP server: its signed record in the HISTOR transparency log — when the tool set was first seen, whether it changed, what the pattern scan found. Never contacts the server asked about.

Current air quality at a place: PM2.5 and PM10 (µg/m³), US and European AQI, from Copernicus CAMS via Open-Meteo, with a signed receipt. Send latitude and longitude, or a city.

Verifiable random bytes for a draw, raffle or tie-break: an ECVRF output over your seed plus a proof anyone can check offline. The same seed always gives the same output, so publish the seed first.