Connect OpenCode to LLMEasy with a custom model

You can connect LLMEasy to OpenCode by first adding credentials with /connect, then declaring LLMEasy as an OpenAI-compatible provider in the config file and selecting a model ID from the GPT Key group.

Prerequisites

LLMEasy API Key (register here)

Install OpenCode

curl
npm

curl -fsSL https://opencode.ai/install | bash

npm install -g opencode-ai

Setup

Automatic setup
Configure via CC Switch
Manual setup

You can run the LLMEasy automatic setup script directly. It only writes the LLMEasy provider configuration and does not replace the installation prerequisites above. The script requires Node.js. If you do not pass an API Key or model explicitly, the script prompts for them when the tool supports interactive input.Follow the step for your operating system. You only need one of them.

If you use macOS / Linux

curl -fsSL https://www.llmeasy.ru/install-opencode-provider.sh | bash

If you use Windows

iwr https://www.llmeasy.ru/install-opencode-provider.ps1 -OutFile "$env:TEMP\install-opencode-provider.ps1"; powershell -ExecutionPolicy Bypass -File "$env:TEMP\install-opencode-provider.ps1"

Clear conflicting environment variables

unset OPENAI_API_KEY
unset OPENAI_BASE_URL

Add the LLMEasy credential with /connect first

Start OpenCode and run:

/connect

In the wizard, choose Other and then:

set the provider id to llmeasy
paste your LLMEasy API Key

OpenCode stores the credential in ~/.local/share/opencode/auth.json.

Edit the OpenCode config file

You can use the global config at ~/.config/opencode/opencode.json or create opencode.json in your project root. The project config has higher precedence.

{
  "$schema": "https://opencode.ai/config.json",
  "model": "llmeasy/YOUR_GPT_MODEL_ID",
  "provider": {
    "llmeasy": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LLMEasy",
      "options": {
        "baseURL": "https://www.llmeasy.ru/v1"
      },
      "models": {
        "YOUR_GPT_MODEL_ID": {
          "name": "YOUR_GPT_MODEL_ID"
        }
      }
    }
  }
}

Replace YOUR_GPT_MODEL_ID with a current GPT Key group model ID copied from the model plaza.

If you want to inline the API key, use this fallback format

{
  "$schema": "https://opencode.ai/config.json",
  "model": "llmeasy/YOUR_GPT_MODEL_ID",
  "provider": {
    "llmeasy": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LLMEasy",
      "options": {
        "baseURL": "https://www.llmeasy.ru/v1",
        "apiKey": "YOUR_API_KEY"
      },
      "models": {
        "YOUR_GPT_MODEL_ID": {
          "name": "YOUR_GPT_MODEL_ID"
        }
      }
    }
  }
}

This is a fallback. The /connect flow above is the preferred setup.

Only use `options.headers` for provider-specific needs

OpenCode’s official docs support custom headers through provider.<id>.options.headers, but this is optional. You usually do not need an extra User-Agent when connecting LLMEasy.If you are also using Helicone, tenant routing, observability, or caching services, add the required headers based on those upstream services’ official docs.

Restart OpenCode

After updating the config file, quit the current OpenCode session and start it again.

Start OpenCode

cd /path/to/your/project
opencode

Notes

Use a GPT Key group model ID as the default model instead of fixed Claude model names
LLMEasy should currently use @ai-sdk/openai-compatible as the OpenAI-compatible provider adapter
If you use /connect, you usually do not need to store the API key directly in the config file
OpenCode’s official docs treat options.headers as optional extended configuration; LLMEasy usually does not need extra headers

​Prerequisites

​Install OpenCode

​Setup

​Related FAQ

​Notes

Prerequisites

Install OpenCode

Setup

Related FAQ

Notes