Call this when an agent needs currently-open EU or German/Austrian public funding calls for a company or project — e.g. to shortlist grants a startup could apply for, or to check what is open in a sector before drafting a proposal. Returns up to 50 normalized EU+DACH funding-opportunity records, refreshed daily. Filters: source, geography, equity_free, consortium_required, deadline_after, deadline_before, open_only.

Options-style volatility regime: ATR percentile and market-regime detection for a futures instrument.

Daily OHLCV candles (open, high, low, close, volume) for BTC/USD and ETH/USD, 1000 days of history (about 2.7 years) refreshed once a day. Source: Binance public market data. No API key needed from the buyer beyond the x402 payment. GET /feed/ohlcv returns the candles; GET /feed/resumen returns last close plus 24h/7d/30d change and 30-day high and low. Built for trading agents that need a clean historical series without running their own data pipeline. Daily interval only. Not financial advice.

Privacy-first OpenAI-compatible text embeddings (768 dims) from a local encoder on dedicated hardware - your text never reaches a third-party cloud. Send {"input": string or array of up to 64 texts}; receive standard OpenAI embeddings JSON with usage. Built for RAG, semantic search, dedupe and clustering in agent pipelines. ~2,000-token limit per text. Pay per call in USDC on Base (x402), no API key or account.

Privacy-first extended inference: the highest output cap (32,768 tokens) on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions for long-form writing, reports, full document drafts, large code outputs (messages array in, chat.completion JSON out). Pay per call in USDC on Base (x402), no API key or account. Pick the cheaper quick/long tiers for shorter work.

Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.

Privacy-first OpenAI-compatible vision: a local vision-language model on dedicated hardware understands your images - they never reach OpenAI/Anthropic or any third-party cloud. Send a public image URL plus a prompt (or OpenAI image_url messages); receive a standard chat.completion JSON answering about the image. Up to 4 images per call (more are clamped). Pay per call in USDC on Base (x402), no API key.

Privacy-first long-form inference: 8,192-token output cap on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions (messages array in, chat.completion JSON out) for summarization, drafting, extraction, translation, code, multi-paragraph answers. Pay per call in USDC on Base (x402), no API key or account. Shorter work? Use the cheaper quick tier (4,096 tokens).

Withdraw tokens from a user's Otto AI Safe to any EOA. Supports 7 chains (Base, Polygon, Arbitrum, Ethereum, BSC, Avalanche, Solana). Non-Base chains require an explicit EOA recipient.

Best-available stablecoin yield deposit options: the highest-APY lending venue per stablecoin (USDC / USDT / DAI …), read directly on-chain from Aave / Morpho / Compound across supported chains, with APY basis, liquidity profile, reward-completeness and TVL. Returns the best available options (not yet personalized to a specific wallet's holdings).

Execute instant same-chain token swaps through LI.FI's DEX aggregation. Supports Base, Ethereum, Polygon, BSC, Arbitrum, Avalanche, and Solana, with best-route execution across major DEXes and liquidity sources.

Tell whether a given date is a Japanese business day. Japanese national holidays and business-day calculations derived from the Cabinet Office official CSV. Returns holidays for a given year, plus business-day arithmetic used by invoicing, logistics and HR systems in Japan.

A user's profile info: id, name, bio, location, follower/following counts, verification. Example: GET /api/jack/info

Send money to a debit card via push-to-card. Supports USD (U.S.), EUR (Eurozone), and GBP (U.K.). Returns a redemption URL to enter card details.

Ad copy and public landing-page URL to evidence-linked checks for missing offer phrases, numbers, CTA and lead-capture elements. Bounded HTML inspection, not rendered-page vision or semantic conversion prediction.

Trade and transaction history for a user's Otto AI Safe account — swaps, bridges, deposits, withdrawals with timestamps and explorer links.

Decide whether an agent-authored bash command complies with an execution policy, using a real shell tokenizer rather than pattern matching. Catches recursive deletes, force pushes, cluster and infrastructure teardown, raw device writes, path escapes, privilege escalation, and curl-piped-to-shell through pipelines, substitutions, quoting games and base64. Returns reason codes with spans and an optional short-lived permit bound to the exact canonical command. Never executes anything.

Search supported ERC-20 tokens by symbol or address across 6 chains (Base, Ethereum, Arbitrum, Polygon, BSC, Avalanche). 5000+ tokens from CoinGecko. Use before swap/bridge to disambiguate tokens.

Spend Check: should you pay this counterparty? Watchtower track record, CDP merchant catalog, and address hygiene combined into a clear/caution/avoid verdict with a signed attestation. $0.005 USDC per check.

A user's followers (~200 per page; paginate with cursor until has_more is false). Example: GET /api/jack/followers