My usage (wallet-keyed purchase

OpenAI's transcription wire on the ten-minute tier: POST multipart/form-data with a `file` part. Same model as /v1/audio/transcriptions with a longer cap, for a recording a four-minute route refuses.

OpenAI-compatible chat completions, pro tier: gpt-4o, gpt-4.1, gpt-6 sol, claude sonnet, gemini pro, grok - paid per call in USDC over x402. Same wire format as /v1/chat/completions with higher input/output caps (48k chars in, 4096 tokens out).

Google's native generateContent wire on the pro tier. Send Gemini's own request shape (contents, systemInstruction, generationConfig, function declarations) and get Gemini's own response shape (candidates, usageMetadata) back. Point a Google GenAI SDK at this gateway and pay per request with USDC, no account. Also answers the Google-shaped path /v1beta/models/<model>:generateContent.

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1/pro and pay $0.10 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+ and Haiku 5.

OpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url https://agent402.tools/v1/pro and pay $0.10 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Responses wire.

Quick research brief on any topic - web search results plus an AI-generated answer in one pass. Article digest skill pack: one x402 payment runs 3 underlying tools (search, answer, search-news); partial-success per step.

Fetch an X (Twitter) account's most recent tweets by user id or username (username is resolved first). Options to exclude retweets and replies, page with pagination_token, or fetch only tweets newer than since_id. Each tweet carries text, created time, language and engagement metrics.

The full macro + crypto dashboard in one call: 5 FRED series, 5 Treasury reads, yield-curve spread, crypto market/trending/global, and live gas - a 14-tool macro + crypto basket, bundled below its a la carte price. Macro dashboard refresh skill pack: one x402 payment runs 14 underlying tools (fred-release-calendar, fed-funds, cpi-yoy, unemployment-rate, sahm-rule, yield-curve-spread, treasury-yiel

Pull live price, market structure, OHLC history, trending status, global market context, and recent news for a single coin in one pass. Crypto research skill pack: one x402 payment runs 7 underlying tools (crypto-price, crypto-market, crypto-history, crypto-trending, crypto-global, search-news, extract); partial-success per step.

OpenAI-compatible text-to-speech over x402 - point any OpenAI SDK's audio.speech.create() at base_url https://agent402.tools/v1 and pay $0.06 per call in USDC, no API key, no signup. Served by Voxtral Mini TTS behind a five-model failover chain (xAI Grok Voice, Kokoro, MAI-Voice-2 Flash, MAI-Voice-2), every link proven by a real paid canary - a provider outage never becomes your failure. Up to 2,0

Convert text to speech with the eleven-v4 model, the most expressive speech tier (inline audio tags such as [whispering] are read as delivery cues). Returns base64-encoded audio. Same interface, voices, formats and backups as /api/tts. No API key needed; pay per call via x402 or MPP. Text capped at 2000 chars. Model-backed.

Freeze frames of an animation under the render contract: the page defines window.renderAt(t). The tool renders the self-contained HTML document in headless Chromium with all network access refused, calls renderAt for each requested time in seconds and returns a PNG still per time (base64) plus one contact-sheet PNG of every still in a grid. For previews and frame checks of canvas, SVG or CSS anima

Load one public URL once in headless Chromium and report what that load measured: navigation timings (TTFB, DOMContentLoaded, load), Web Vitals read from the page's own performance entries (LCP, FCP, CLS, total blocking time from long tasks), total transfer bytes, request count, the 5 heaviest resources, render-blocking scripts and styles, console errors, and an opportunities array computed from t

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.

A synthesized answer to a natural-language question, grounded in a live web search and returned with source citations (URL, snippet). Use it when an agent needs a direct, current answer plus the receipts to verify or follow up, instead of reading several pages itself.

Run 2-5 web searches in one call with a 20% volume discount vs. individual searches. Each query returns ranked results (title, URL, snippet). Ideal for multi-faceted research or comparing sources on different aspects of a topic. If some queries fail upstream, the call returns the ones that succeeded with an error on each failed query and is charged; a call where every query fails is not charged.

Search public tweets from the last 7 days on X (Twitter) by query, using X API v2 search operators (keywords, from:, #hashtag, lang:, -is:retweet). Returns up to 10 tweets per call with text, created time, language, engagement metrics (likes, retweets, replies, quotes, impressions) and the author's username flattened onto each row, plus a next_token for paging.

OpenAI-compatible image generation over x402 - point any OpenAI SDK's images.generate() at base_url https://agent402.tools/v1 and pay $0.08 per image in USDC, no API key, no signup. Served by FLUX.2 Pro with GPT-5 Image Mini as the failover; prompt in (up to 4k chars), one 1024x1024 PNG out as inline base64 (response_format b64_json). One image per call (n locked to 1). Optional zdr:true routes on

Cryptographic hash of a text string - sha256 (default), sha512, sha1 or md5 - returned as hex and base64. Use it for content fingerprints, integrity checks and deterministic ids; pure computation, instant.