Second opinion: three different AI models (gpt-oss-120b, Llama 3.3 70B, Gemma 4) answer independently, then you get the consensus, the points they disagree on, a confidence level and a combined best answer. Also callable as GET with the same fields as query parameters.

Answer grader: scores a draft answer 0-10 against the question, a rubric and/or source URLs, lists factual errors and unsupported claims with fixes, and returns an improved answer. A self-check before an agent ships. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on Moonshot Kimi K2.7 Code, a coding and software-agent model with tool calling (262K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/kimi-code and pay per token with x402 instead of an API key: $1.9 per million input and $8 per million output tokens, minimum $0.002 a call, at most $0.1742. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool call

OpenAI-compatible chat completions on Zhipu GLM-5.3, frontier reasoning with tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/glm5 and pay per token with x402 instead of an API key: $2.8 per million input and $8.8 per million output tokens, minimum $0.002 a call, at most $0.2322. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, stre

OpenAI-compatible chat completions on Moonshot Kimi K2.6, an agentic model built for long tool-calling workflows (262K context). Set your OpenAI SDK base URL to https://agentrxi.com/v1/kimi and pay per token with x402 instead of an API key: $1.9 per million input and $8 per million output tokens, minimum $0.002 a call, at most $0.1742. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, re

Turn a video clip into a palette-optimised animated GIF: start, duration (up to 15 s), fps (4-20) and width (100-800 px). Also callable as GET with the same fields as query parameters.

Ask a document: give a web page, PDF, Word, Excel or CSV URL (or raw text) and a question; get an answer backed by exact quotes from the document. Long documents are searched with embeddings first. Also callable as GET with the same fields as query parameters.

Rent a real Chrome browser for up to 60 minutes: opens a live session (optionally at a URL) and returns a session id, a screenshot, the page text and the clickable controls. Drive it step by step with /v1/browser/act (click, type, press, scroll, select, go back). The session stays open 10 minutes after each action. Also callable as GET with the same fields as query parameters.

Bulk reader: up to 20 web pages read and cleaned to text in one call (instead of 20 separate calls), each trimmed to your character limit. Unreadable pages are flagged, not failed. Also callable as GET with the same fields as query parameters.

Convert office documents with LibreOffice: Word, Excel, PowerPoint, OpenDocument, RTF, HTML, CSV or text to PDF (default), or between formats (docx, odt, rtf, txt, html, xlsx, ods, csv, pptx, odp). Also callable as GET with the same fields as query parameters.

Cut a clip out of an audio or video file: give start and end (seconds or hh:mm:ss) or duration. mode=precise re-encodes for frame-exact cuts (default); mode=fast copies streams instantly but cuts on keyframes. Also callable as GET with the same fields as query parameters.

OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on DeepSeek R1 Distill (Qwen 32B), chain-of-thought reasoning model. Set your OpenAI SDK base URL to https://agentrxi.com/v1/r1 and pay per token with x402 instead of an API key: $0.994 per million input and $9.762 per million output tokens, minimum $0.002 a call, at most $0.1084. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (reasoning, streaming supported), up t

OpenAI-compatible chat completions on Alibaba Qwen 3.8 27B, the newest Qwen with reasoning, tool calling and a 262K context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/qwen3.8 and pay per token with x402 instead of an API key: $0.9 per million input and $6.4 per million output tokens, minimum $0.002 a call, at most $0.1039. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, r

OpenAI-compatible chat completions on DeepSeek V4 Pro, a top open frontier model with reasoning, tool calling and a 1M-token context. Set your OpenAI SDK base URL to https://agentrxi.com/v1/deepseek-pro and pay per token with x402 instead of an API key: $2.64 per million input and $7.92 per million output tokens, minimum $0.002 a call, at most $0.2158. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI

Convert audio or video between formats with ffmpeg: mp4, webm, mov, mkv, mp3, wav, ogg, opus, m4a, aac, flac. Optional width, fps, crf, audio_bitrate, sample_rate and channels. Up to 20 MB in, 150 s of processing. Also callable as GET with the same fields as query parameters.

Error fixer for coding agents: paste an error message or stack trace (plus optional code) and get the likely cause and a concrete fix with code, researched from live sources (Stack Overflow, GitHub issues, docs) with citations. Also callable as GET with the same fields as query parameters.

Pull the audio track out of a video as mp3 (default), wav, m4a, aac, flac, ogg or opus, ready for transcription or editing. Also callable as GET with the same fields as query parameters.

Wallet activity alerts: watch any wallet on Base, Ethereum, Arbitrum, Optimism or Polygon for 7 days; every incoming or outgoing transfer (ETH, tokens, NFTs) is POSTed to your webhook URL within about 10 minutes. Check status with the watch id. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on NVIDIA Nemotron 3 120B, agentic reasoning with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/nemotron and pay per token with x402 instead of an API key: $1.5 per million input and $4.5 per million output tokens, minimum $0.002 a call, at most $0.0254. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming suppo