Api x402 offerings

LLM inference API: OpenAI-compatible chat completions for 100+ AI models (DeepSeek, GPT, Claude, Gemini, Grok, GLM, Qwen, Kimi, Llama, Mistral). Suited for AI agents that need on-demand text generation, coding or tool calling paid per request in USDC on Base with x402: no account, no API key. Model in body.model (GET /v1/models); streaming supported. Exact price in the 402 quote; automatic refund if the model fails.

LLM inference proxy - send an OpenAI-format chat/completions request and get a response from GPT-4o-mini (or gpt-6-luna by its id). Supports vision (up to 2 image URLs, low detail) and structured output (response_format: json_object or json_schema). No API key needed; pay per call via x402. Input capped at 16k chars, output at 4096 tokens.

LLM inference proxy (Premium tier) - o3 or gpt-5.6-terra reasoning models (default gpt-5.6-terra; the retired o3-mini and o4-mini ids are served by gpt-5.6-terra). Supports vision (up to 2 image URLs) and structured output (response_format: json_object or json_schema).

LLM inference proxy (Pro tier) - GPT-4o or GPT-4.1 (or gpt-6.1-sol by its id). Supports vision (up to 2 image URLs) and structured output (response_format: json_object or json_schema). No API key needed; pay per call via x402. Input capped at 16k chars, output at 2048 tokens.

LONG Events events API: global electronic-music event discovery with structured artists. Actions: discover, list, stats, catalog_stats, spotlight_candidates, get_sets, get_now_playing, get_schedule, search_artists, get_artist, get_artist_events, list_artists. Artist-action identity objects include nullable mbid and verified spotify_id; artist event payloads include the resolved closest-to-purchase ticket_url.

Machine-readable commercial map of this catalog: featured endpoints, cheapest calls, the free tier and the credit plans, so an agent can plan a budget in one request.

LLM inference as a pay-per-call commodity — ask anything (?q=...) and get the first live answer from a multi-provider failover chain (Groq, Gemini, paid tiers when configured). One flat price, any subject, no API keys...

One x402 payment, 2-5 catalog endpoints in a single response. Pass ?paths=/a,/b,/c (any priced endpoint up to the item cap) or omit it and the node auto-picks from YOUR own probe history. Failed items are refunded pro...

One call, any task: describe what you need in plain English (?task=) and this node routes it — local semantic search (MiniLM ONNX, cross-encoder rerank) over its own live catalog — to the best in-budget endpoint, EXEC...

Which endpoint should you buy for your task? Paid catalog concierge: send ?task=<plain English> and get the single best Losbeto endpoint for it — ranked by local semantic search (MiniLM ONNX with cross-encoder rerank)...

Score up to 100 x402 endpoints in one call. For teams: per-agent spend limits and an audit trail at lumierepaycheck.org/subscribe.

Score up to 100 x402 endpoints in one call. For teams: per-agent spend limits and an audit trail at lumierepaycheck.org/subscribe.

Search the LupaRiel catalog of agentic payment rails by name, slug, tag or category. Returns up to 20 matching entries as JSON, not the full catalog.

Rail matrix for agent payments in Argentina: which rail settles, which handles consent and which handles checkout for a given case.

Discover which Macaroon Network service, endpoint, or data product to call next. Searches Macaroon's own published catalogue -- title, category, description, price, and trust evidence metadata -- and returns a short, source-linked ranked list plus a safe recommended next call for each match. A thin wrapper over this registry's own existing semantic search and router infrastructure; does not execute matched services, does not call any underlying paid endpoint, and does not duplicate a matched ser

Enriched context for a single match: the teams, venue, status, and surrounding tournament state, addressable by event, event URN, or team and opponent on a date.

Resolves a provider id (api_football, sportradar, opta, entain, espn) or canonical machina URN to the entity it identifies, with all cross-provider ids attached.

Enriched context for a single match: the teams, venue, status, and surrounding tournament state, addressable by event, event URN, or team and opponent on a date.

Enriched context for a single match: the teams, venue, status, and surrounding tournament state, addressable by event, event URN, or team and opponent on a date.

A call bundle: 500 API calls within 4 hours for one $1 payment, the per-call rate in one settlement. Returns a token for the X-MMNM-Pass header on any API call (an agents or log page spends 5, the export 25, a seller check 5). Unused calls expire; no refunds.

Read what arrived at your webhook inbox (from /paid/inbox/create): method, headers (cookies and auth removed), query and body of each delivery, newest last. Pass after= the last id you saw to get only new ones; delete=1 clears what you read. No free trial.

Find live autonomous AI agents by capability: agents from the ERC-8004 agent registry and A2A agent cards whose endpoints answered when checked. Returns names, descriptions and A2A/MCP endpoints.

Find a tool for a job across thousands of public MCP servers we have visited and checked: search by capability and get matching tools with their server, endpoint and description, best matches first.

Chat completion from an open AI model (Llama 3.3 70B by default; Llama 3.1 8B for speed), no account or API key: send messages (or a prompt), get the model's reply. Up to 24,000 characters in and 1,024 tokens out per call.