AI models & inference

OpenAI-compatible chat completions over x402 (local GPU models, no API key) — Genesis402 / UnyKorn Operator Network

x402engine — Quick image generation using FLUX Schnell (~2s, good for drafts)

x402engine — Generate text embeddings using OpenAI text-embedding-3-small — for semantic search, clustering, RAG

x402engine — High-quality image generation using FLUX.2 Pro (~5s, production-ready)

Convert text to natural-sounding audio via ElevenLabs (returns base64 MP3). Pay per call with USDC (x402) or credits - archtools.dev

Continuous load is the sum of the running watts of all appliances marked as simultaneous. The surge check adds the largest single starting surge on top of the continuous load, which is the case that trips an inverter; simultaneous starts of two motors are reported separately as a second figure. Starting factors and power factors are design rules of thumb per appliance class and are stated in the response, they are not device data.

Substantive llms.txt repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Substantive llms.txt decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Substantive llms.txt audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

GPTBot access repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

GPTBot access decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

ClaudeBot access repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

ClaudeBot access decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

ClaudeBot access audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

x402engine — Google's low-cost multimodal model for high-volume agent workloads

x402engine — Zhipu AI's flagship model — strong multilingual and reasoning performance

x402engine — OpenAI's higher-compute Luna tier for efficient long-context reasoning

x402engine — AionLabs' compact reasoning model for efficient general-purpose inference

x402engine — Google's fastest and cheapest model — ideal for high-volume, low-latency tasks

x402engine — Meituan's long-context model for reasoning, coding, and high-volume inference

x402engine — MiniMax's latest model — improved reasoning and generation with 204k context

x402engine — MiniMax's efficient model — fast and affordable for everyday tasks

x402engine — DeepSeek's stronger V4 model — advanced reasoning, coding, and long-context analysis

x402engine — OpenAI's efficient GPT-5.6 tier with a 1M-token context window

x402engine — Tencent's efficient reasoning model with a 262k-token context window

x402engine — GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while

x402engine — Mistral's code-focused model — optimized for software development and technical tasks

x402engine — OpenAI's cheapest GPT-5 tier — ultra-affordable for high-volume agent tasks

x402engine — Alibaba's latest model — 1M context, strong multilingual and coding capabilities

x402engine — Alibaba's flagship open model — excellent multilingual and coding capabilities