All Services

Returns a writing style profile for a Bluesky author, including persona embedding, top keywords, style summary, and post count

Retrieves Bluesky posts from a specific author within a given time window, including engagement metrics like likes, reposts, quotes, and replies.

Probe a live x402-protected endpoint to validate its HTTP 402 challenge, payment requirements, and marketplace listing before authorizing payment.

Probes an x402-protected URL without paying it, then scores and grades its 402 challenge quality for payment readiness and Bazaar discoverability.

Checks whether an x402 paid endpoint is currently live by probing it for a valid payment challenge, counting well-formed priced offers, and returning a single payable_now flag along with any payment-breaking warnings.

Probes an x402-enabled endpoint to reveal its payment requirements (price, network, asset, payTo address) and declared schemas without sending any payment.

Probes a URL for x402 payment requirements and decodes its payment terms before committing to pay

Provides pay-per-call access to Anthropic's Claude Opus 5.5 flagship model for advanced reasoning, coding, and long-horizon agentic tasks via HTTP 402 micropayments

Runs OpenAI GPT-4o Mini inference via pay-per-call HTTP 402 micropayment, returning OpenAI-compatible chat completions

Runs OpenAI GPT-5 Nano chat completions via pay-per-call HTTP 402 micropayment, returning an OpenAI-compatible response

Runs inference on Mistral AI's Devstral (devstral-2512) coding-focused LLM via a pay-per-call HTTP 402 micropayment endpoint

Runs a chat completion request through Cohere's Command-A model, paid per-call via USDC micropayment on Base, MegaETH, or Solana.

Calls OpenAI's GPT-5.1 model via a pay-per-call HTTP 402 micropayment endpoint, returning OpenAI-compatible chat completions

Runs inference on MoonshotAI's Kimi K3 frontier multimodal model with 1M token context window, optimized for agentic tasks, via pay-per-call micropayment

Sends a chat message to Google's Gemini 3.5 Flash Lite model and returns an OpenAI-compatible response, billed per call via USDC micropayment over HTTP 402

Runs DeepSeek's low-latency V4 Flash model for ultra-low-cost reasoning and coding tasks with up to 1M token context, accessible via x402 micropayment at $0.003 USDC per call

Calls Google Gemini 3 Pro via a pay-per-call HTTP 402 micropayment endpoint, returning an OpenAI-compatible chat completion response

Runs a GPT-5.6-Luna-Pro chat completion request via micropayment-gated API, returning an OpenAI-compatible response for $0.00486 USDC per call.

Runs the KAT-Coder-Pro v2.5 coding-specialized language model via pay-per-call HTTP 402 micropayment, returning OpenAI-compatible chat completions

Runs Google's Gemini 3 Flash model via an OpenAI-compatible chat completions interface, pay-per-call with USDC micropayments

Runs inference on DeepSeek's re-post-trained V4 Flash revision with enhanced agentic capabilities, coding, and reasoning over a 1M-token context window, billed per call via x402 micropayments.

Runs Anthropic's Claude Haiku model via a pay-per-call HTTP 402 micropayment endpoint for fast, affordable text generation

Runs inference on DeepSeek V4 Pro via a pay-per-call HTTP 402 micropayment endpoint, returning OpenAI-compatible chat completions

Runs Claude Sonnet 5 (Anthropic) inference via a pay-per-call HTTP 402 micropayment endpoint, returning OpenAI-compatible chat completions

Calls OpenAI GPT-4o via HTTP 402 micropayment, returning an OpenAI-compatible chat completion response for a given message array.

Run inference on Meta's Llama 4 Maverick model via a pay-per-call HTTP 402 micropayment API, returning OpenAI-compatible chat completions

Sends a chat completion request to Google Gemini 3.1 Pro via a pay-per-call HTTP 402 micropayment API, returning an OpenAI-compatible response

Provides pay-per-call access to Mistral AI's Mistral Large 4 frontier multimodal model for reasoning, coding, and agentic tasks with a 512K-token context window

Runs inference on DeepSeek V3.2 Speciale, a large language model, accessible via HTTP 402 micropayment at $0.003274 USDC per call.

Generates a single 1024×1024 PNG image at high quality using GPT Image 2.5 Flare, billed per call via x402 micropayment

Calls Anthropic's Claude Haiku 5.5 model (small, fast, cost-efficient) for high-volume tasks like summarization, coding, and subagent use via pay-per-call micropayment

Call Anthropic's Claude Opus 4.8 model via a pay-per-call HTTP 402 micropayment endpoint, returning OpenAI-compatible chat completions

Runs DeepSeek V3.2 chat completions with tool calling, streaming, and advanced sampling via pay-per-call micropayment on Base/Solana

Run DeepSeek R1 inference with OpenAI-compatible chat completions, paid per-call via HTTP 402 micropayment in USDC

Provides pay-per-call access to Anthropic's Claude Sonnet 5.5 model via an OpenAI-compatible chat completions API, billed at $0.028871 USDC per call via HTTP 402 micropayments.

Runs a DeepSeek flagship chat/reasoning model inference call via pay-per-use HTTP 402 micropayment, returning the model's text response

Run Xiaomi's MiMo-V2.6-Flash 309B Mixture-of-Experts language model via pay-per-call HTTP 402 micropayments, returning OpenAI-compatible chat completions.

Clones a voice from a reference audio URL and synthesizes new speech from text at 48kHz quality

Runs inference on Anthropic's Claude Opus 4.5 model via a pay-per-call HTTP 402 micropayment API, returning OpenAI-compatible chat completions.

Runs inference on Alibaba's Qwen3.7-Plus large language model via pay-per-call HTTP 402 micropayment, returning OpenAI-compatible chat completions.

Runs inference on Meta's Llama 3.3 70B Instruct model via a pay-per-call HTTP 402 micropayment API, returning OpenAI-compatible chat completions

Run inference against the Aion-3.0 large language model via pay-per-call HTTP 402 micropayment, with tool-calling and streaming support

Calls OpenAI GPT-5.4 via HTTP 402 micropayment, returning an OpenAI-compatible chat completion response

Sends a chat conversation to Anthropic's Claude Opus model and returns a completion, billed per call via HTTP 402 micropayment in USDC

Runs inference on Alibaba's Qwen3.7-Max large language model via a pay-per-call HTTP 402 micropayment endpoint

Calls the MiniMax M3 large language model via pay-per-call HTTP 402 micropayment, returning an OpenAI-compatible chat completion response.

Performs neural web search with highlighted snippets across articles, news, research, and general web content, returning ranked results with optional full-page text.

Converts up to 2000 bytes of text into MP3 audio using Voxtral Mini, offering 30 preset voices across English, British, and French accents with emotional tones

Answers questions using a search-augmented LLM (Perplexity) that grounds responses in real-time web search with citations

Call Google's Gemini 3.1 Flash Lite model via pay-per-call HTTP 402 micropayment, with full OpenAI-compatible chat messaging, tool use, streaming, and multimodal input support.

Run inference on Alibaba's Qwen 2.5 72B Instruct language model via a pay-per-call HTTP 402 micropayment API

Animates a public image URL into a 5-second video using Kling V3 Pro, guided by a motion and camera direction prompt

Simulates an EVM transaction before broadcast, returning gas estimates, execution traces, and revert reasons

Captures a screenshot of any public URL, optionally as a full-page capture, for $0.01 USDC per call via HTTP 402 micropayment.

Generates a 5-second 768p landscape video with native audio from a text prompt using MiniMax H3, billed per call via x402 micropayment.

Generates a high-quality image from a text prompt using FLUX.2 Pro, returning a production-ready result in approximately 5 seconds

Generates images with accurately rendered text using Ideogram v3, optimized for logos, signage, and any visual requiring legible embedded typography

Generates images quickly (~2 seconds) from a text prompt using the FLUX Schnell model, optimized for rapid drafts and prototypes

Generates text embeddings using OpenAI text-embedding-3-small for semantic search, clustering, and RAG pipelines, paid per-call via x402 micropayments

Search for hotels by location and date range, returning properties with prices, ratings, and amenities via Google Hotels (powered by SerpApi).

Call Alibaba's Qwen3 8B Omni Flash multimodal model (text, image, audio, video) via a pay-per-call HTTP 402 micropayment API

Calls Anthropic's Claude Sonnet 4.6 LLM via a pay-per-call HTTP 402 micropayment endpoint, returning an OpenAI-compatible chat completion response.

Runs inference on OpenAI's o1 reasoning model via a pay-per-call HTTP 402 micropayment endpoint, returning an OpenAI-compatible chat completion response.

Generates a production-quality 5-second video clip using Kling V3 Pro from a text prompt, with configurable aspect ratio and negative prompt, via HTTP 402 micropayment at $0.70 USDC per call.

Call OpenAI's o4-mini reasoning model via pay-per-call HTTP 402 micropayment, returning an OpenAI-compatible chat completion response.

Send a chat completion request to xAI's Grok 4.5 model and receive a response, billed per-call via HTTP 402 micropayment in USDC

Send OpenAI-compatible chat messages to Z-AI's GLM-5.3 language model and receive generated text responses, paid per-call via USDC micropayment.

Transcribes up to 10 minutes of audio to text with speaker diarization, accepting either a URL or base64-encoded audio

Calls OpenAI GPT-5.2 Pro via a pay-per-call HTTP 402 micropayment endpoint, returning an OpenAI-compatible chat completion response

Runs Qwen3 Coder model inference via pay-per-call HTTP 402 micropayment, returning OpenAI-compatible chat completions optimized for code generation and reasoning.

Runs the Qwen 3.5 Plus language model via a pay-per-call HTTP 402 micropayment endpoint, returning OpenAI-compatible chat completions

Runs arbitrary code in an isolated sandbox supporting Python, JavaScript, Bash, and R, returning stdout/stderr and results

Swaps a face from a reference image into an AI-generated scene described by a text prompt, returning a new composited image

Resolves an ENS name to an Ethereum address, or reverse-resolves an EVM address to its primary ENS name

Returns current USDC and USDT USD prices plus gas cost estimates for Base and Tron network transfers

Independently verifies an x402 payment endpoint by comparing what a seller declares (price, payTo, network, method) against what a live observer sees right now, returning field-level discrepancy evidence with classification and a signed receipt.

Fetches and extracts headlines from any RSS feed URL, paid per-call in USDC via the x402 protocol — no API keys or accounts required.

Fetches a public webpage and returns its clean, readable text content — billed at $0.02 USDC per call via the x402 protocol, no API key required.

Returns a Wikipedia article summary for a given topic, paid per call in USDC on Base via the x402 protocol

Fetches the latest SEC EDGAR filings (10-K, 10-Q, 8-K) for a given US stock ticker, paid per call in USDC via x402

Returns a real-time foreign exchange rate for a specified currency pair, paid per call in USDC via the x402 protocol

Scans text or source code for accidentally-committed secrets such as API keys, tokens, and private keys before publication.

Fetches a Jupiter aggregator swap quote preview for a given input/output token pair and trade amount on Solana.

Returns hourly weather forecast data (up to 240 hours) for any lat/lon coordinate, including temperature, precipitation, wind, humidity, and cloud cover.

Returns the live aggregated probability of which party controls the House after the next election, always resolving to the current active market instance and rolling forward automatically.

Returns the latest SEC 8-K filings classified as bankruptcy and receivership (Item 1.03) as structured JSON with extractive summaries and filing links.

Returns rain probability and expected weather conditions for Houston across a specified time window, for use in scheduling and event planning decisions.

Returns weather-driven flight delay risk scores for a US airport across four 6-hour blocks covering the next 24 hours, with named meteorological drivers and a one-line verdict.

Returns the latest SEC 8-K filings classified as executive and board leadership changes (Item 5.02) as structured JSON with summaries and filing links

Returns per-venue implied and vig-adjusted probabilities with order book depth for a prediction market, plus cross-venue spread and disagreement flag.

Returns the live consensus probability that Bitcoin will trade above $100k at year end, aggregated across Kalshi and Polymarket, with auto-roll to the next annual instance on resolution.

Returns the live prediction-market probability that the current Atlantic hurricane season will produce more named storms than the 30-year average (14.4), aggregated across venues like Kalshi.

Returns 1–7 day daily energy-weather forecasts for a US grid region, including heat/cooling degree days, solar/wind generation indices, peak load signal, and extreme risk flags.

Returns a quarter-over-quarter diff of an institutional manager's 13F-HR SEC filing: new positions, exits, increases, decreases (with share deltas), and top-10 concentration changes.

Returns 6-hour block weather-driven delay risk scores for Denver International Airport (DEN) over the next 48 hours, covering wind gusts, convective activity, winter precipitation, and cloud cover.

Returns an hourly weather forecast (temperature, precipitation probability, wind) for Las Vegas up to 168 hours out, using NWS-derived data bias-blended with a calibrated local station model.

Returns only the economic data observations that have been printed or revised since a given cursor, enabling efficient incremental polling of US economic dashboard data.

Returns the live market-implied probability that the Fed will hike rates at its next FOMC meeting, with auto-rolling to the current instance and cross-venue aggregation.

Returns 6-hour block weather-driven flight delay risk scores for Houston Bush Intercontinental Airport (IAH) over the next 48 hours, based on wind gusts, convective potential, precipitation, and cloud cover.

Returns real-time prediction market probability that the awards-season favorite will win Best Picture at the next Oscars, aggregated from Polymarket and Kalshi.