For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://modelgates.ai/docs/_mcp/server.

OpenCode

What is OpenCode?

OpenCode is an open-source AI coding agent available as a terminal interface and desktop app (beta). It features LSP integration, multi-session support, sharable session links, and compatibility with 75+ LLM providers — including ModelGates for unified multi-model access through a single API key.

Quick Start

Step 1: Install OpenCode

bash
curl -fsSL https://opencode.ai/install | bash
bash
npm install -g opencode-ai
bash
brew install anomalyco/tap/opencode

For additional installation methods (Bun, pnpm, Yarn, Arch Linux, Windows), see the OpenCode installation docs.

Step 2: Get Your ModelGates API Key

  1. Sign up or log in at ModelGates
  2. Navigate to your API Keys page
  3. Create a new API key
  4. Copy your key (starts with sk-mg-...)

Step 3: Connect OpenCode to ModelGates

OpenCode supports ModelGates as a built-in provider. Use the interactive /connect command:

  1. Start OpenCode in your project directory:
bash
cd /path/to/your/projectopencode
  1. Run the /connect command and select ModelGates:
text
/connect
  1. Paste your ModelGates API key when prompted.

  2. Run /models to select a model:

text
/models

Your requests will now be routed through ModelGates.

Alternative: Config File

You can also configure ModelGates directly in your opencode.json config file:

json
{  "$schema": "https://opencode.ai/config.json",  "provider": {    "modelgates": {      "models": {        "anthropic/claude-sonnet-4": {},        "google/gemini-2.5-flash": {}      }    }  }}

Set your API key via the /connect command or by adding it to ~/.local/share/opencode/auth.json:

json
{  "modelgates": {    "type": "api",    "key": "sk-mg-your-key-here"  }}

Provider Routing

When using ModelGates, you can control which upstream providers handle your requests by adding options.provider to individual models in your config:

json
{  "$schema": "https://opencode.ai/config.json",  "provider": {    "modelgates": {      "models": {        "anthropic/claude-sonnet-4": {          "options": {            "provider": {              "order": ["anthropic"],              "allow_fallbacks": true            }          }        }      }    }  }}

For a full breakdown of routing options, see the Provider Routing docs.

Why Use ModelGates with OpenCode?

Access to Hundreds of Models

Switch between any model available on ModelGates — Anthropic, OpenAI, Google, xAI, Meta, DeepSeek, and many more — without managing separate API keys for each provider.

Provider Failover

If one provider is unavailable or rate-limited, ModelGates automatically routes to another, keeping your coding sessions uninterrupted.

Organizational Controls

For teams, ModelGates provides centralized budget management. Set spending limits, allocate credits, and monitor usage across developers using OpenCode from your ModelGates Activity Dashboard.

Model Flexibility

Switch models by updating your config or using the /models command — no need to reconfigure API keys or endpoints.

Troubleshooting

  • Auth Errors: Ensure your API key is set correctly via /connect. Check at modelgates.ai/keys.
  • Model Not Found: Verify the model ID on modelgates.ai/models. Use the exact format (e.g., anthropic/claude-sonnet-4).
  • Privacy: ModelGates does not log your source code prompts unless you opt in to prompt logging. See our Privacy Policy for details.

Resources