Back to guides

OpenCode Integration

Connect OpenCode to 180+ models through LLM Gateway. One config file, any model, full cost tracking.

OpenCode is an open-source AI coding agent for your terminal, IDE, or desktop. This guide shows you how to connect it to LLM Gateway—giving you access to 180+ models from 60+ providers, all tracked in one dashboard.

Prerequisites

Before starting, you need to install OpenCode. Visit the OpenCode download page to install OpenCode for your platform (Windows, macOS, or Linux).

After installation, verify it works by running:

1opencode --version

Configuration Steps

Setting up OpenCode with LLM Gateway requires creating a configuration file and connecting your API key.

Step 1: Create Configuration File

Create a file named config.json in the OpenCode configuration directory:

Location:

Windows:

1C:\Users\YourUsername\.config\opencode\config.json

macOS/Linux:

1~/.config/opencode/config.json

File contents:

1{
2  "provider": {
3    "llmgateway": {
4      "npm": "@ai-sdk/openai-compatible",
5      "name": "LLM Gateway",
6      "options": {
7        "baseURL": "https://api.llmgateway.io/v1"
8      },
9      "models": {
10        "gpt-5": {
11          "name": "GPT-5"
12        },
13        "gpt-5-mini": {
14          "name": "GPT-5 Mini"
15        },
16        "google/gemini-2.5-pro": {
17          "name": "Gemini 2.5 Pro"
18        },
19        "anthropic/claude-3-5-sonnet-20241022": {
20          "name": "Claude 3.5 Sonnet"
21        }
22      }
23    }
24  },
25  "model": "llmgateway/gpt-5"
26}

Configuration explained:

  • npm: The adapter package OpenCode uses to communicate with OpenAI-compatible APIs
  • baseURL: LLM Gateway's API endpoint
  • models: The models you want to use (you can add more from our models page)
  • model: Your default model selection

Step 2: Launch OpenCode and Connect Provider

Start OpenCode from your terminal:

1opencode

In VS Code/Cursor:

  1. Install the OpenCode extension from the marketplace
  2. Open Command Palette (Ctrl+Shift+P or Cmd+Shift+P)
  3. Type "OpenCode" and select "Open opencode"

Once OpenCode launches, run the /connect command to connect to LLM Gateway:

OpenCode Connect Command

Step 3: Select LLM Gateway Provider

In the provider list, scroll down to find "LLM Gateway" under the "Other" section and select it:

Select LLM Gateway Provider

Step 4: Enter Your API Key

OpenCode will prompt you for your API key. Enter your LLM Gateway API key and press Enter:

Enter API Key

OpenCode will automatically save your credentials securely.

Where to get your API key:

Sign up for LLM Gateway and create an API key from your dashboard.

Step 5: Start Using OpenCode

You're all set! OpenCode is now connected to LLM Gateway. You can start asking questions and building with AI:

OpenCode Ready

Try asking OpenCode about your project or request help with coding tasks:

OpenCode in Action

Why Use LLM Gateway with OpenCode?

  • 180+ models — GPT-5, Claude, Gemini, Llama, and more from 60+ providers
  • One API key — Stop juggling credentials for every provider
  • Cost tracking — See what each coding session costs in your dashboard
  • Response caching — Repeated requests hit cache automatically
  • Volume discounts — The more you use, the more you save

Adding More Models

You can add any model from the models page to your configuration. Simply add more entries to the models object in your config.json:

1{
2  "provider": {
3    "llmgateway": {
4      "models": {
5        "gpt-5": { "name": "GPT-5" },
6        "gpt-5-mini": { "name": "GPT-5 Mini" },
7        "deepseek/deepseek-chat": { "name": "DeepSeek Chat" },
8        "meta/llama-3.3-70b": { "name": "Llama 3.3 70B" }
9      }
10    }
11  }
12}

After updating config.json, restart OpenCode to see the new models.

Switching Models

To change your default model, update the model field in your configuration:

1{
2  "model": "llmgateway/gpt-5-mini"
3}

Or select a different model directly in the OpenCode interface.

Troubleshooting

OpenCode asks for API key every time

Make sure the provider ID in your config.json matches exactly: "llmgateway" (all lowercase, no spaces).

404 Not Found errors

Verify your baseURL is set to https://api.llmgateway.io/v1 (note the /v1 at the end).

Models not showing up

After editing config.json, restart OpenCode completely for changes to take effect.

Connection timeout

Check that you have an active internet connection and that your API key is valid from the dashboard.

Configuration Tips

  • Global configuration: Use ~/.config/opencode/config.json to apply settings across all projects
  • Project-specific: Place opencode.json in your project root to override global settings for that project
  • Model selection: You can specify different models for different types of tasks using OpenCode's agent configuration

Get Started

Ready to enhance your OpenCode experience? Sign up for LLM Gateway and get your API key today.