LLM Gateway Developer Resources

This section is for developers building applications on top of LLM Gateway — with our command-line tool, the MCP server, the Vercel AI SDK via our first-party provider package @llmgateway/ai-sdk-provider, and TanStack AI via the first-party @tanstack/ai-llmgateway adapter.

API entry points

• OpenAPI specification — typed request, response, and error schemas
• Authentication — API keys and access control
• Developer dashboard — projects, keys, usage, and budgets
• API versioning and deprecation policy — compatibility and retirement notices

Guides

• DevPass Usage API — Show monthly and weekly DevPass allowance meters in your application
• LLM Gateway CLI — Launch coding agents, scaffold projects from templates, generate agent configs, and manage keys, budgets, and usage from the terminal
• Model Context Protocol (MCP) — Use LLM Gateway as an MCP server from Claude Code, Cursor, and other MCP clients
• Using the AI SDK — Install the provider, generate and stream text, call tools, and wire up Next.js routes
• Image Generation with the AI SDK — Generate images with generateImage and stream image output through chat
• Using TanStack AI — Stream chat with useChat, call tools, and surface reasoning through the first-party @tanstack/ai-llmgateway adapter

Why the AI SDK

The AI SDK gives you one TypeScript interface for text generation, streaming, tool calling, and image generation. Combined with LLM Gateway, a single provider instance and one API key reach every model in the catalog — see the models page for what's available.

Other ways to integrate

If you're not using the AI SDK:

• Use any OpenAI-compatible SDK against https://api.llmgateway.io/v1 — see the Quickstart
• Use the Anthropic SDK against the Anthropic-compatible endpoint
• Call the REST API directly — see the API reference in the sidebar