agentbox-inference

Generate chat completions via an OpenAI-compatible API with USDC micropayments.

14|1|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/cascade-protocol/agentbox --skill agentbox-inference
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentbox-inference
Source: https://github.com/cascade-protocol/agentbox/tree/main/skills/agentbox-inference
Command: npx skills add https://github.com/cascade-protocol/agentbox --skill agentbox-inference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides access to powerful Large Language Models (LLMs) for text generation and chat completions, enabling complex AI-driven content creation and analysis tasks.

Core Features & Use Cases

  • LLM Inference: Generate text using various OpenAI-compatible models like Kimi K2.5 and MiniMax M2.5.
  • Paid API Access: Leverages a pay-per-request model with automatic USDC micropayments via the x_payment tool.
  • Use Case: You need to generate a concise summary of a technical document using a high-quality LLM, or compare the output of different models for a specific task.

Quick Start

Use the agentbox-inference skill to generate a chat completion using the 'moonshotai/kimi-k2.5' model with the message 'Explain x402 in one sentence'.

Frequently Asked Questions about agentbox-inference

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

FAQPage Schema
How do I generate chat completions using an OpenAI-compatible API?

You can generate chat completions by using this Skill to access OpenAI-compatible models like Kimi K2.5 and MiniMax M2.5. It processes your text prompts and returns generated text responses through a standard inference API endpoint.

What is automatic USDC micropayment for LLM inference?

Automatic USDC micropayment is a pay-per-request mechanism handled by the x_payment tool. It processes transactions transparently to grant access to paid LLM inference services without manual billing steps for each API call.

Can I compare LLM outputs for different text generation models?

Yes, you can compare LLM outputs by sending identical prompts to different supported models. The Skill processes requests for various models like Kimi K2.5 and MiniMax M2.5, allowing you to evaluate and compare their generated text results.

Do I need a specific payment tool to use paid LLM inference?

Yes, you need the x_payment tool to handle automatic USDC micropayments. It processes the required pay-per-request transactions, enabling access to the chat completion and text generation services provided by the LLM models.

What are the limitations of using USDC micropayments for API text generation?

The primary limitation is the strict dependency on the x_payment tool for automatic USDC transactions. If the micropayment processing fails or lacks sufficient funds, the LLM inference API call will not execute and no text will be generated.