skills.rest
lucacadalora
lucacadaloraCOMMUNITY
Explore all skills by this author →
GitHub

jatevo

Configure OpenClaw with Jatevo API for free OpenAI-compatible LLM inference.

46|9|Updated Mar 21, 2026
Search Tags:#model routing#chat completions#openai-compatible#openclaw#free tier#llm inference#api key setup
One-click install
npx skills add https://github.com/lucacadalora/jatevo-openclaw --skill jatevo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jatevo
Source: https://github.com/lucacadalora/jatevo-openclaw/tree/main
Command: npx skills add https://github.com/lucacadalora/jatevo-openclaw --skill jatevo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of paying for LLM access by giving OpenClaw users free, production-grade inference through a single API key using OpenAI-compatible endpoints.

Core Features & Use Cases

  • Free inference-as-a-service: Zero-cost access to Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7 for everyday agent and chat workloads.
  • OpenAI-compatible configuration: Drop-in compatibility with OpenClaw model-provider settings so you can use standard LLM tooling without vendor lock-in.
  • Use Case: Deploy an OpenClaw assistant that can handle long-document Q&A with Qwen (1M context), reasoning-heavy tasks with Kimi (262K context), or ultra-low-latency chat with GLM (128K context).

Quick Start

Run the included setup script by executing: bash setup.sh.

Frequently Asked Questions about jatevo

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

FAQPage Schema
How do I get free OpenAI-compatible LLM inference for OpenClaw?▼

You can get free OpenAI-compatible LLM inference for OpenClaw by configuring it with the Jatevo API, which provides zero-cost access to models like Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7.

What models are available for long-context document analysis and reasoning tasks via the Jatevo API?▼

The Jatevo API provides access to Qwen 3.5 Plus for 1M context document analysis, Kimi K2.5 for 262K context reasoning tasks, and GLM 4.7 for 128K context ultra-low-latency chat.

Do I need an API key to use OpenAI-style chat completions with OpenClaw?▼

Yes, you need a valid Jatevo API key prefixed with 'jk_' to satisfy OpenAI-style chat-completions requests and authenticate your OpenClaw configuration.

How do I configure OpenClaw to use a free OpenAI-compatible endpoint?▼

To configure OpenClaw, run the setup script via 'bash setup.sh', which sets the correct baseUrl, auth header, and model IDs to enable OpenAI-compatible endpoint communication.

Can I use OpenClaw with standard LLM tooling without vendor lock-in?▼

Yes, OpenClaw achieves drop-in compatibility with standard LLM tooling without vendor lock-in by using OpenAI-compatible configuration settings for the Jatevo API.

What are the limitations of using free inference-as-a-service for OpenClaw workloads?▼

Free inference-as-a-service limitations are not explicitly defined, but it requires a valid Jatevo API key and is suited for agent, chat, long-document Q&A, reasoning, and batch processing workloads.

Related Skills

Explore More Software Engineering Skills→
polymerdaopolymerdao
1

polymer-pay-llm

Route OpenAI-compatible chat completions through Polymer Pay's category-based provider routing.

Official
Advanced
xiaotianfotosxiaotianfotos
579

claude-in-tmux

Manage Claude Code CLI in tmux sessions for background tasks and logging.

Community
Intermediate
sayalinvidiasayalinvidia

nemoclaw-user-configure-inference

Configure NemoClaw to route sandboxed inference to local OpenAI-compatible endpoints.

Community
Intermediate
cascade-protocolcascade-protocol
14

agentbox-inference

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

Official
Intermediate