Ozeki AI Gateway

This guide demonstrates how to create a user account in Ozeki AI Gateway. User accounts are required to generate API keys that applications use to authenticate with the gateway. You'll learn how to navigate to the Users section, add a new user, provide user details including name and email, and complete the creation process. Once created, the user account appears in the users list and is ready for API key generation and route configuration.

This guide demonstrates how to configure AI service provider connections in Ozeki AI Gateway. Providers are the connection points to external AI services like OpenAI or Anthropic. You'll learn how to add a new provider, configure connection details including API endpoint and authentication credentials, and test the provider to ensure it's working correctly. The guide includes video tutorials and step-by-step instructions with screenshots.

This guide demonstrates how to create routes in Ozeki AI Gateway that connect users to AI providers. You'll learn how to navigate to the Routes section and configure the necessary mappings between users, API keys, and providers. Routes enable centralized access control, determining which users can access which providers and models through your gateway infrastructure. The guide includes quick steps and a video tutorial.

This guide covers various AI client applications and how to set them up with Ozeki AI Gateway. Each section provides detailed instructions for installing, configuring, and using different AI coding assistants and interfaces including Open WebUI, Kilo Code, Cline, Claude Code, and Open Code. Learn how to enhance your development workflow with artificial intelligence capabilities through these tested client integrations.

OpenWebUI

Kilo Code

Cline

Claude Code

OpenCode

This page contains guides for creating API keys from various AI providers and configuring them in Ozeki AI Gateway. Each guide provides step-by-step instructions for obtaining an API key from platforms including OpenAI, DeepSeek, OpenRouter, Mistral, POE, GLM, Kimi K2, and Qwen. Learn how to set up each provider in your gateway for centralized access to multiple AI models through a unified interface.

OpenAI

DeepSeek

OpenRouter

Mistral

POE

GLM

Moonshot Kimi

Qwen

Azure OpenAI

Vertex AI

Anthropic

AWS Bedrock

LiteLLM

AI/ML API

DeepInfra

Fireworks AI

Github Models

Groq

Helicone

Heroku

HuggingFace

Nebius

Novita AI

Nvidia NIM

Ollama

OVHCloud

Perplexity

Replicate

SambaNova

Together AI

Vercel AI Gateway

vLLM

xAI

Xinference

This page contains comprehensive guides for running local AI models on various hardware configurations, including dual GPU setups with NVIDIA RTX 6000 Pro and RTX 5090 cards. Learn how to set up vLLM, configure Ollama, and optimize your local AI infrastructure for efficient large language model inference. Topics include installation steps, GPU communication solutions, and specific commands for high-performance models.

Explore practical examples and step-by-step solutions for common AI integration challenges. These guides demonstrate how to resolve technical issues and optimize your AI infrastructure using Ozeki AI Gateway. Learn how to fix missing think tags for Kimi K2.5 and other real-world problems that developers encounter when working with AI models and gateways.