DocsAPI ReferenceSDKsCookbookChangelog

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

LangChain

Using LangChain

LangChain provides a standard interface for working with chat models. You can use ModelGates with LangChain using the dedicated ChatModelGates integration packages. For more details on LangChain's model interface, see the LangChain Models documentation.

Resources:

typescript
import { ChatModelGates } from "@langchain/modelgates"; const model = new ChatModelGates(  "anthropic/claude-sonnet-4.6",  { temperature: 0.8 }); // Example usageconst response = await model.invoke([  { role: "system", content: "You are a helpful assistant." },  { role: "user", content: "Hello, how are you?" },]);

For full documentation — including streaming, tool calling, structured output, reasoning, multimodal inputs, provider routing, and more — see the LangChain integration guides: