For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://modelgates.ai/docs/_mcp/server.
Anthropic Agent SDK
The Anthropic Agent SDK lets you build AI agents programmatically using Python or TypeScript. Since the Agent SDK uses Claude Code as its runtime, you can connect it to ModelGates using the same environment variables.
Configuration
Set the following environment variables before running your agent:
export ANTHROPIC_BASE_URL="https://modelgates.ai/api"export ANTHROPIC_AUTH_TOKEN="$MODELGATES_API_KEY"export ANTHROPIC_API_KEY="" # Important: Must be explicitly emptyTypeScript Example
Install the SDK:
npm install @anthropic-ai/claude-agent-sdkCreate an agent that uses ModelGates:
import { query } from "@anthropic-ai/claude-agent-sdk"; // Environment variables should be set before running:// ANTHROPIC_BASE_URL=https://modelgates.ai/api// ANTHROPIC_AUTH_TOKEN=your_openrouter_api_key// ANTHROPIC_API_KEY="" async function main() { for await (const message of query({ prompt: "Find and fix the bug in auth.py", options: { allowedTools: ["Read", "Edit", "Bash"], }, })) { if (message.type === "assistant") { console.log(message.message.content); } }} main();Python Example
Install the SDK:
pip install claude-agent-sdkCreate an agent that uses ModelGates:
import asynciofrom claude_agent_sdk import query, ClaudeAgentOptions # Environment variables should be set before running:# ANTHROPIC_BASE_URL=https://modelgates.ai/api# ANTHROPIC_AUTH_TOKEN=your_openrouter_api_key# ANTHROPIC_API_KEY="" async def main(): async for message in query( prompt="Find and fix the bug in auth.py", options=ClaudeAgentOptions( allowed_tools=["Read", "Edit", "Bash"] ) ): print(message) asyncio.run(main())Tip: The Agent SDK inherits all the same model override capabilities as Claude Code. You can use ANTHROPIC_DEFAULT_SONNET_MODEL, ANTHROPIC_DEFAULT_OPUS_MODEL, and other environment variables to route your agent to different models on ModelGates. See the Claude Code integration guide for more details.