elyan-compute

Submit pay-per-request AI inference and media generation jobs via HTTP endpoints.

72|6|Updated Feb 20, 2026
One-click install
npx skills add https://github.com/Scottcjn/elyan-compute-skill --skill elyan-compute
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elyan-compute
Source: https://github.com/Scottcjn/elyan-compute-skill/tree/main
Command: npx skills add https://github.com/Scottcjn/elyan-compute-skill --skill elyan-compute

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires x402_fetch.

What problem does it solve?

This Skill solves the problem of getting fast, on-demand AI inference and media generation without managing local GPU hardware or handling payment complexity yourself.

Core Features & Use Cases

  • Remote GPU inference: Run LLM prompt inference on Elyan Labs GPU endpoints for tasks like question answering and text generation.
  • Multimodal compute: Generate image understanding outputs from a provided image URL using the vision endpoint.
  • Media generation & delivery: Produce TTS audio (WAV) and video outputs by submitting prompts and receiving results via pay-per-request endpoints.
  • Micropayments workflow: Uses x402 USDC micropayments on Base (chain 8453) and supports an alternate RustChain RTC payment header.

Quick Start

Ask your agent to submit an LLM inference job through elyan-compute using x402 USDC on Base for a single request and return the JSON result.

Frequently Asked Questions about elyan-compute

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run remote GPU inference without managing local hardware?

Remote GPU inference without local hardware is enabled by submitting HTTP job payloads to dedicated endpoints. You send prompts to these remote endpoints for LLM text generation, vision analysis, TTS audio, and video generation, bypassing local GPU setup entirely.

Can I use USDC micropayments on Base to pay for AI video generation?

Yes, USDC micropayments on Base (chain 8453) can be used to pay for AI video generation. The x402 payment protocol facilitates pay-per-request billing, automatically returning HTTP 402 responses to prompt your agent for USDC payment before processing.

What is the x402 payment protocol for remote AI compute?

The x402 payment protocol is an HTTP-based mechanism for handling USDC micropayments on Base. It enables pay-per-request remote AI compute by returning HTTP 402 status codes when payment is required, allowing automated agents to seamlessly handle transactions for inference and media generation.

Does x402_fetch support text-to-speech and vision generation requests?

Yes, x402_fetch supports text-to-speech and vision generation requests by routing payloads to remote GPU endpoints. It handles the USDC micropayment routing on Base, returning HTTP 200 results containing WAV audio or image understanding outputs upon successful processing.

Why does my remote inference request return an HTTP 402 or 503 error?

Remote inference requests return HTTP 402 when a USDC payment is required but not yet processed, and HTTP 503 when GPU availability is insufficient. These errors indicate your agent must handle the x402 payment flow or retry the job payload when compute resources free up.