Get started

Introduction to LLM Gateway Overview Quickstart

AI Gateway

Airside for Providers Anthropic API Compatibility LLM Gateway Authentication, API Keys & IAM Rules Audit Logs Compliance Cost Breakdown Custom Providers Data Retention Document Reading Dynamic Routes Embeddable Payments Embeddings Guardrails Image Generation Master Keys Metadata Org Models Directory Moderations OCR Organization skills Project access Realtime API Reasoning Rerank Response Healing Routing Service Tiers Sessions Source Attribution Speech Generation Request Timeouts Transcription Video Generation Vision Support Native Web Search

Provider Cache Control Gateway Caching

Microsoft Entra ID Okta Google Workspace

Developers

LLM Gateway Developer Resources DevPass Usage API LLM Gateway CLI LLM Gateway MCP Server Using the AI SDK Image Generation with the AI SDK AI SDK Gateway protocol Using TanStack AI

DevPass & Coding Tools

Agent Skills Autohand Code Integration Claude Code Integration Cline Integration Codex CLI Integration Continue CLI Integration Crush Integration Cursor Integration DevPass Code Integration Empryo Integration GitHub Copilot App Integration Hermes Agent Integration Kilo Code Integration Kimi Code Integration MiMo Code Integration N8n Integration OpenClaw Integration OpenCode Desktop Integration OpenCode Integration Pi Integration Reasonix Integration

Knowledge base

References

Health check GET Create speech POST Create transcription POST Chat Completions POST Embeddings POST Edit image POST Create image POST Retrieve key status GET Anthropic Messages POST Models GET Moderations POST OCR POST Rerank POST Video content GET Create video POST Video log content GET Retrieve video GET

All systems operational

Guides

N8n Integration

Connect n8n workflow automation to LLM Gateway for AI-powered workflows

n8n is a powerful workflow automation tool that can be enhanced with AI capabilities through LLM Gateway. This guide shows how to integrate LLM Gateway into your n8n workflows.

n8n workflow with LLM Gateway

Using DevPass? This integration also works with a DevPass plan key. Use canonical model IDs without a provider prefix (claude-sonnet-4-5, not anthropic/claude-sonnet-4-5) — provider-pinned routing is not available on coding plans; the gateway picks the provider for you.

Prerequisites

An LLM Gateway account with an API key
n8n instance (self-hosted or cloud)
Basic understanding of n8n workflows

Setup

The easiest way to use LLM Gateway with n8n is through the OpenAI node with custom configuration.

Add OpenAI Credentials

In n8n, go to Settings → Credentials

n8n credentials

Click Add Credential → OpenAI

n8n credentials

Configure as follows:
- API Key: Your LLM Gateway API key
- Base URL: https://api.llmgateway.io/v1
- Organization ID: Leave blank

n8n credentials

Configure OpenAI Node

Add an AI Agent node to your workflow
Add a Chat Model edge to the node

n8n credentials

Configure the node to use the LLMGateway provider

n8n credentials

Note: You have to toggle off the responses API. LLMGateway does not support it.

responses api

Select your desired options

Model: Use any LLMGateway model ID (e.g., gpt-5)
Options: Optionally, configure LLM parameters

n8n credentials

Test Workflow

Finally, try running your workflow with a test prompt.

n8n credentials

How is this guide?

Last updated on

MiMo Code Integration

Use GPT-5.5, Claude, Gemini, Kimi K3, or 200+ models with MiMo Code. Custom provider configuration in a few steps, with full cost tracking.

OpenClaw Integration

Use GPT-5.4, Claude Opus, Gemini, or any model with OpenClaw across Discord, WhatsApp, Telegram, and more

On this page

Prerequisites Setup Add OpenAI Credentials Configure OpenAI Node Test Workflow

Ready for production?

Ship to production with SSO, audit logs, spend controls, and guardrails your security team will approve.

Explore Enterprise