OpenWork

OpenWork is an AI workspace built on OpenCode primitives that helps individuals and teams connect, manage, and customize their AI stack inside a project. It supports flexible model integration through workspace-level configuration, allowing users to add custom or managed LLM providers, work with local or hosted models, and extend capabilities through reusable skills. This makes OpenWork a practical platform for organizing and scaling AI-powered workflows across different projects and teams.

Account & API Keys Setup

The first step to start using Infron is to create an account and get your API key.

Setup Guide

OpenWork is built on OpenCode primitives, Support everything that you could modify in .opencode.json, like adding a model.

You can find the corresponding model names here and configure them in the path below. You also have the option to configure multiple models simultaneously.

Inside ~/.config/opencode/opencode.json:

Example

{
  "$schema": "https://opencode.ai/config.json",
  "model": "infron/anthropic/claude-sonnet-4.6",
  "provider": {
    "infron": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Infron",
      "options": {
        "baseURL": "https://llm.onerouter.pro/v1",
        "apiKey": "{env:INFRON_API_KEY}"
      },
      "models": {
        "anthropic/claude-opus-4.7": {
          "name": "Claude Opus 4.7"
        },
        "anthropic/claude-sonnet-4.6": {
          "name": "Claude Sonnet 4.6"
        },
        "anthropic/claude-haiku-4.5": {
          "name": "Claude Haiku 4.5"
        },
        "z-ai/glm-5": {
          "name": "GLM 5"
        },
        "z-ai/glm-5.1": {
          "name": "GLM 5.1"
        },
        "z-ai/glm-4.7": {
          "name": "GLM 4.7"
        },
        "moonshotai/kimi-k2.5": {
          "name": "Kimi K2.5"
        },
        "moonshotai/kimi-k2-thinking": {
          "name": "Kimi K2 Thinking"
        },
        "qwen/qwen3.6-plus": {
          "name": "Qwen 3.6 Plus"
        },
        "qwen/qwen3.5-plus": {
          "name": "Qwen 3.5 Plus"
        },
        "qwen/qwen3-max": {
          "name": "Qwen3 Max"
        },
        "qwen/qwen3-coder-plus": {
          "name": "Qwen3 Coder Plus"
        }
      }
    }
  }
}