OpenCode 是一款开源的 AI 编程代理工具，提供终端界面、桌面应用和 IDE 扩展等多种使用方式。本文介绍如何在 OpenCode 中配置与使用腾讯云大模型 Token Plan 企业版。
前置条件
在开始配置前，确保您已完成以下准备工作：
1. 订阅 Token Plan 企业版套餐。
2. 获取模型配置。
3. 获取 API Key。
安装 OpenCode
npm install -g opencode-ai
安装完成后，您可以执行如下命令检查，输出版本号则表示安装成功。
opencode -v
配置 Token Plan 企业版
您需要按照下面的示例修改 OpenCode 的配置文件，配置文件路径如下，配置文件不存在时新建即可。
macOS / Linux：
~/.config/opencode/opencode.json。Windows：
C:\\Users\\<用户名>\\.config\\opencode\\opencode.json。说明：
请您将代码中 <USER_API_KEY> 替换为您的 API Key。下方配置已根据套餐类型预填了
models 列表，可按需保留所需模型。{"$schema": "https://opencode.ai/config.json","provider": {"myprovider": {"npm": "@ai-sdk/openai-compatible","name": "Tencent Cloud Token Plan 企业版 专业套餐","options": {"baseURL": "https://tokenhub.tencentmaas.com/plan/v3","apiKey": "<USER_API_KEY>"},"models": {"auto": {"name": "Auto","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 196608,"output": 32768}},"glm-5": {"name": "GLM-5","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 204800,"output": 131072}},"glm-5.1": {"name": "GLM-5.1","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 204800,"output": 131072}},"glm-5.2": {"name": "GLM-5.2","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 131072}},"glm-5-turbo": {"name": "GLM-5-Turbo","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 204800,"output": 131072}},"kimi-k2.5": {"name": "Kimi-K2.5","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 262144,"output": 262144}},"kimi-k2.6": {"name": "Kimi-K2.6","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 262144,"output": 262144}},"minimax-m2.5": {"name": "MiniMax-M2.5","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 204800,"output": 131072}},"minimax-m2.7": {"name": "MiniMax-M2.7","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 204800,"output": 131072}},"minimax-m3": {"name": "MiniMax-M3","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 131072}},"deepseek-v4-flash": {"name": "DeepSeek-V4-Flash","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 393216}},"deepseek-v4-pro": {"name": "DeepSeek-V4-Pro","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 393216}},"deepseek-v4-flash-202605": {"name": "DeepSeek-V4-Flash 原厂直供","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 393216}},"deepseek-v4-pro-202606": {"name": "DeepSeek-V4-Pro 原厂直供","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 1048576,"output": 393216}}}}}}
{"$schema": "https://opencode.ai/config.json","provider": {"myprovider": {"npm": "@ai-sdk/openai-compatible","name": "Tencent Cloud Token Plan 企业版 轻享套餐","options": {"baseURL": "https://tokenhub.tencentmaas.com/plan/v3","apiKey": "<USER_API_KEY>"},"models": {"auto": {"name": "Auto","modalities": {"input": ["text"],"output": ["text"]},"options": {"thinking": {"type": "enabled","budgetTokens": 8192}},"limit": {"context": 196608,"output": 32768}}}}}}
使用 OpenCode
执行如下命令启动 OpenCode：
opencode
输入
/models，选择配置的模型并在 OpenCode 中使用。完成上述配置后，即可开始使用 OpenCode。
