# LLM Gateway Documentation

> Documentation for LLM Gateway - a full-stack LLM API gateway

## Docs

- [Introduction](/): LLM Gateway is an open-source API gateway for Large Language Models. Route requests to multiple providers, manage API keys, track usage, and optimize costs.
- [Overview](/overview): Introduction to LLM Gateway, an open-source API gateway for LLMs.
- [Quickstart](/quick-start): Fastest way to start using LLM Gateway in any language or framework.
- [Self Host LLMGateway](/self-host): Simple guide to self-hosting LLMGateway using Docker.
- [Health check](/health): LLM Gateway health check endpoint to verify the API is reachable and returning a 200 response.
- [Chat Completions](/v1_chat_completions): Create OpenAI-compatible chat completions through LLM Gateway. Route requests to any supported model across OpenAI, Anthropic, Google, and 20+ providers.
- [Anthropic Messages](/v1_messages): Send requests using the Anthropic Messages API format through LLM Gateway and route them to any supported provider with a unified interface.
- [Models](/v1_models): List all available AI models supported by LLM Gateway, including pricing, context window, and capability metadata for each provider.
- [Moderations](/v1_moderations): Classify text or multimodal inputs with OpenAI-compatible moderation through LLM Gateway to detect unsafe or policy-violating content.
- [Create Video](/v1_videos): Create an asynchronous video generation job through LLM Gateway using the OpenAI-compatible video API across supported providers.
- [Video Content](/v1_videos_content): Stream the generated video content from LLM Gateway once the asynchronous video generation job has completed successfully.
- [Retrieve Video](/v1_videos_retrieve): Retrieve the current state and metadata of an LLM Gateway video generation job, including progress, status, and output details.
- [Anthropic API Compatibility](/features/anthropic-endpoint): Use the Anthropic-compatible endpoint to access any LLM model through the familiar Anthropic API format.
- [API Keys & IAM Rules](/features/api-keys): Comprehensive guide to API key management and Identity Access Management (IAM) rules for fine-grained access control
- [Audit Logs](/features/audit-logs): Track all organization activity with comprehensive audit logs
- [Caching](/features/caching): Reduce costs and latency by caching identical requests.
- [Cost Breakdown](/features/cost-breakdown): Get real-time cost information for each API request directly in the response.
- [Custom Providers](/features/custom-providers): Learn how to integrate custom OpenAI-compatible providers with LLMGateway for enhanced flexibility and control.
- [Data Retention](/features/data-retention): Store and access your full request and response data for debugging, analytics, and compliance.
- [Embeddings](/features/embeddings): Generate vector embeddings using OpenAI-compatible embedding models.
- [Guardrails](/features/guardrails): Protect your LLM usage with content guardrails that detect and block harmful content
- [Image Generation](/features/image-generation): Generate images using AI models through the OpenAI-compatible images API or chat completions API
- [Master Keys](/features/master-keys): Provision projects and gateway API keys programmatically with org-scoped bearer tokens (Enterprise only)
- [Metadata](/features/metadata): Send additional context and metadata to LLM Gateway using custom headers.
- [Moderations](/features/moderations): Classify unsafe text and image inputs with the OpenAI-compatible moderations API
- [Reasoning](/features/reasoning): Learn how to use reasoning-capable models that show their step-by-step thought process.
- [Response Healing](/features/response-healing): Automatically repair malformed JSON responses from AI models.
- [Routing](/features/routing): Learn how LLMGateway intelligently routes your requests to the best available models and providers.
- [Source Attribution](/features/source): Use the X-Source header to identify your domain for public usage statistics.
- [Video Generation](/features/video-generation): Generate videos with an OpenAI-compatible async API and signed completion callbacks
- [Vision Support](/features/vision): Learn how to send images to vision-enabled models using URLs or inline base64 data.
- [Native Web Search](/features/web-search): Enable real-time web search capabilities to get up-to-date information from the internet.
- [Agent Skills](/guides/agent-skills): Packaged instructions and guidelines for AI coding agents
- [Autohand Code Integration](/guides/autohand): Use GPT-5, Claude, Gemini, or any model with Autohand Code's autonomous coding agent. Simple config, full cost tracking.
- [Claude Code Integration](/guides/claude-code): Use GPT-5, Gemini, or any model with Claude Code. Three environment variables, full cost tracking.
- [LLM Gateway CLI](/guides/cli): Command-line tool for scaffolding and managing LLM Gateway projects
- [Cline Integration](/guides/cline): Use LLM Gateway with Cline for AI-powered coding assistance in VS Code
- [Codex CLI Integration](/guides/codex-cli): Use any model with OpenAI's Codex CLI through LLM Gateway. One config file, full cost tracking.
- [Continue CLI Integration](/guides/continue): Use any model with Continue CLI through LLM Gateway. One config file, 210+ models, full cost tracking.
- [Cursor Integration](/guides/cursor): Use LLM Gateway with Cursor IDE — supported in plan mode only. Cursor's coding agent does not work with external OpenAI-compatible endpoints.
- [Hermes Agent Integration](/guides/hermes-agent): Use any model with Hermes Agent through LLM Gateway. One config change, full cost tracking, 210+ models.
- [Kilo Code Integration](/guides/kilo-code): Use LLM Gateway with Kilo Code in VS Code. Built-in provider — just search, connect your API key, and start coding.
- [Model Context Protocol (MCP)](/guides/mcp): Use LLM Gateway as an MCP server for Claude Code, Cursor, and other MCP-compatible clients
- [N8n Integration](/guides/n8n): Connect n8n workflow automation to LLM Gateway for AI-powered workflows
- [OpenClaw Integration](/guides/openclaw): Use GPT-5.4, Claude Opus, Gemini, or any model with OpenClaw across Discord, WhatsApp, Telegram, and more
- [OpenCode Desktop Integration](/guides/opencode-desktop): Connect OpenCode Desktop to 210+ models through LLM Gateway. No config files — just open Settings, connect, and start building.
- [OpenCode Integration](/guides/opencode): Connect OpenCode to 210+ models through LLM Gateway's built-in provider. No config files needed — just select, authenticate, and code.
- [Pi Integration](/guides/pi): Use any model with Pi coding agent through LLM Gateway — GPT-5.5, Gemini, Claude, DeepSeek, and 200+ others in your terminal.
- [AWS Bedrock Integration](/integrations/aws-bedrock): Connect AWS Bedrock to LLM Gateway for access to foundation models
- [Azure Integration](/integrations/azure): Connect Azure to LLM Gateway for enterprise-grade OpenAI models
- [Vertex AI Anthropic Integration](/integrations/vertex-anthropic): Connect Google Cloud Vertex AI to LLM Gateway to run Claude models on your own GCP project
- [Activity](/learn/activity): View and inspect every API request made through LLM Gateway
- [Agents](/learn/agents): Monitor your AI coding agents and their activity
- [API Keys](/learn/api-keys): Create, limit, and control API keys for authenticating with LLM Gateway
- [Audit Logs](/learn/audit-logs): Track every action taken within your organization
- [Billing](/learn/billing): Manage your credits, subscription plan, and payment methods
- [Dashboard](/learn/dashboard): Your central hub for monitoring LLM usage, costs, and performance
- [Guardrails](/learn/guardrails): Configure content safety rules to protect your LLM usage
- [Introduction](/learn): Learn how to navigate and use the LLM Gateway dashboard
- [Model Usage](/learn/model-usage): Track usage breakdown by individual model
- [Org Preferences](/learn/org-preferences): Manage your organization's name, billing email, and billing details
- [Group Chat](/learn/playground-group): Watch multiple AI models discuss and collaborate on your prompt
- [Image Studio](/learn/playground-image): Generate and edit images using AI models
- [Video Studio](/learn/playground-video): Generate videos using AI models
- [Chat Playground](/learn/playground): Test LLM models interactively with a full-featured chat interface
- [Policies](/learn/policies): Configure data retention and other organization policies
- [Preferences](/learn/preferences): Configure project-level settings including caching and project mode
- [Provider Keys](/learn/provider-keys): Bring your own provider API keys to use without additional fees
- [Referrals](/learn/referrals): Earn credits by referring other users to LLM Gateway
- [Security Events](/learn/security-events): Monitor guardrail violations and content policy events
- [Team](/learn/team): Manage team members and their roles within your organization
- [Transactions](/learn/transactions): View your complete payment and credit history
- [Usage & Metrics](/learn/usage-metrics): Detailed analytics for requests, models, errors, caching, and costs
- [Migrate from LiteLLM](/migrations/litellm): Switch from self-hosted LiteLLM to managed LLM Gateway. Same API format, zero infrastructure to maintain.
- [Migrate from OpenRouter](/migrations/openrouter): Switch to LLM Gateway for built-in analytics, self-hosting options, and simpler API. Two-line code change.
- [Migrate from Vercel AI Gateway](/migrations/vercel-ai-gateway): Keep your Vercel AI SDK code, add response caching, detailed analytics, and smart routing. One provider for all models.
- [Rate Limits](/resources/rate-limits): Understanding rate limits for free and paid models on LLMGateway.