AI Service Providers tested with Ozeki AI Gateway
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 the respective platform and setting it up as a provider in your Ozeki AI Gateway installation.
OpenAI provides access to powerful language models including GPT-4 through a developer API. This guide walks you through generating a secret API key in the OpenAI dashboard and registering it as a provider in Ozeki AI Gateway so your users can access OpenAI models through a centralized interface.
How to create an OpenAI API key to use in Ozeki AI Gateway
DeepSeek offers high-performance language models through an OpenAI-compatible API. This guide covers generating an authentication token on the DeepSeek platform and configuring it as a provider in Ozeki AI Gateway.
How to create a DeepSeek API key to use in Ozeki AI Gateway
OpenRouter is a unified API gateway that gives you access to dozens of AI models from different providers through a single endpoint. This guide shows how to generate an OpenRouter API key and connect it to Ozeki AI Gateway as a provider.
How to create an OpenRouter API key to use in Ozeki AI Gateway
Mistral AI develops efficient open-weight language models available through a cloud API. This guide explains how to create an API key on the Mistral platform and set it up as a provider in Ozeki AI Gateway, including steps to test the connection with a sample prompt.
How to create a Mistral API key to use in Ozeki AI Gateway
POE is a platform that provides access to multiple AI models through a single subscription. This guide walks you through obtaining a POE API key and registering it as a provider in Ozeki AI Gateway for centralized access management.
How to create an POE API key to use in Ozeki AI Gateway
GLM is a series of language models developed by Zhipu AI, accessible through the Z.AI platform. This guide covers creating an API key on Z.AI and adding GLM as a provider in Ozeki AI Gateway.
How to create a GLM API key to use in Ozeki AI Gateway
Kimi K2 is a capable language model from Moonshot AI with strong reasoning and coding abilities. This guide demonstrates how to generate a Kimi K2 API key on the Moonshot AI platform and configure it as a provider in Ozeki AI Gateway.
How to create a Kimi K2 API key to use Ozeki AI Gateway
Qwen is Alibaba Cloud's family of large language models, available through the Model Studio platform. This guide explains how to generate a Qwen API key and connect it to Ozeki AI Gateway so your users can access Qwen models through your infrastructure.
How to create a Qwen API key to use Ozeki AI Gateway
Azure OpenAI provides enterprise-grade access to OpenAI models hosted on Microsoft's cloud infrastructure. This guide covers deploying an Azure OpenAI resource, retrieving the API key and endpoint URL from the Azure portal, and registering it as a provider in Ozeki AI Gateway.
How to create an Azure OpenAI API key to use in Ozeki AI Gateway
Vertex AI gives you access to Google's Gemini models through the Google AI Studio platform. This guide shows how to generate an API key and configure Vertex AI as a provider in Ozeki AI Gateway for access to Gemini Pro and other Google models.
How to create a Vertex AI API key to use in Ozeki AI Gateway
Anthropic develops the Claude family of language models, known for their strong reasoning and safety focus. This guide walks you through creating an API key on the Anthropic platform and setting up Claude as a provider in Ozeki AI Gateway.
How to create an Anthropic API key to use in Ozeki AI Gateway
Amazon Bedrock provides access to foundation models from multiple AI providers through AWS infrastructure. This guide covers generating a long-term API key in the AWS console and connecting Amazon Bedrock to Ozeki AI Gateway as a provider.
How to create a Bedrock API key to use in Ozeki AI Gateway
LiteLLM Proxy is a self-hosted proxy server that provides a unified interface for accessing multiple AI backends. This guide explains how to generate a virtual API key in the LiteLLM admin panel and register it as a provider in Ozeki AI Gateway.
How to create a LiteLLM Proxy API key to use in Ozeki AI Gateway
AI/ML API aggregates models from a variety of providers through a single OpenAI-compatible endpoint. This guide covers obtaining an API key from the AI/ML API dashboard and adding it as a provider in Ozeki AI Gateway.
How to create an AI ML API key to use in Ozeki AI Gateway
DeepInfra hosts a wide selection of open-source language models on managed GPU infrastructure. This guide shows how to generate an API key on the DeepInfra dashboard and set it up as a provider in Ozeki AI Gateway.
How to create a DeepInfra API key to use in Ozeki AI Gateway
Fireworks AI specializes in high-speed inference for open-source language models. This guide explains how to create an API key on the Fireworks AI platform and connect it to Ozeki AI Gateway as a provider.
How to create a Fireworks AI API key to use in Ozeki AI Gateway
GitHub Models provides access to hosted AI models directly through the GitHub platform using a personal access token. This guide covers generating a fine-grained token in your GitHub developer settings and configuring it as a provider in Ozeki AI Gateway.
How to create a Github Models API key to use in Ozeki AI Gateway
Groq is known for its exceptionally fast AI inference using custom LPU hardware. This guide walks you through creating an API key in the Groq console and registering Groq as a provider in Ozeki AI Gateway.
How to create a Groq API key to use in Ozeki AI Gateway
Helicone is an observability and proxy platform for AI APIs that sits between your application and AI providers. This guide covers generating a Helicone API key and setting it up as a provider in Ozeki AI Gateway.
How to create a Helicone API key to use in Ozeki AI Gateway
Hugging Face hosts thousands of open-source models and provides serverless inference through its API. This guide explains how to generate an access token in your Hugging Face profile settings and configure it as a provider in Ozeki AI Gateway.
How to create a HuggingFace API key to use in Ozeki AI Gateway
Nebius AI Studio offers managed inference for open-source language models on European cloud infrastructure. This guide covers obtaining an API key from the Nebius Token Factory and adding Nebius as a provider in Ozeki AI Gateway.
How to create a Nebius AI Studio API key to use in Ozeki AI Gateway
Novita AI provides cost-effective inference for a broad range of open-source language and image models. This guide shows how to generate an API key on the Novita AI platform and connect it to Ozeki AI Gateway as a provider.
How to create a Novita AI Studio API key to use in Ozeki AI Gateway
Nvidia NIM provides optimized AI inference microservices for a range of language and multimodal models through the Nvidia Build platform. This guide explains how to generate an API key and configure Nvidia NIM as a provider in Ozeki AI Gateway.
How to create an Nvidia NIM API key to use in Ozeki AI Gateway
Ollama makes it easy to run open-source language models locally on your own machine with a simple API. This guide covers setting up an Ollama API key and registering a local Ollama instance as a provider in Ozeki AI Gateway.
How to create an Ollama API key to use in Ozeki AI Gateway
OVHCloud AI Endpoints provides managed inference for open-source models on European cloud infrastructure with a focus on data sovereignty. This guide covers generating an API key in the OVHCloud Manager and adding it as a provider in Ozeki AI Gateway.
How to create an OVHCloud AI Endpoints API key to use in Ozeki AI Gateway
Perplexity AI offers language models with built-in web search capabilities, making them useful for queries that require up-to-date information. This guide explains how to obtain a Perplexity API key and set it up as a provider in Ozeki AI Gateway.
How to create a Perplexity AI API key to use in Ozeki AI Gateway
SambaNova Cloud delivers high-throughput AI inference on custom dataflow hardware. This guide demonstrates how to generate an API key on the SambaNova platform and register it as a provider in Ozeki AI Gateway.
How to create a SambaNova API key to use in Ozeki AI Gateway
Together AI provides cloud inference for a large collection of open-source language and embedding models at competitive prices. This guide shows how to create a Together AI API key and connect it to Ozeki AI Gateway as a provider.
How to create a Together AI API key to use in Ozeki AI Gateway
Vercel AI Gateway is a managed proxy that routes requests to multiple AI providers through a single unified endpoint. This guide covers obtaining an API key from Vercel and setting up Vercel AI Gateway as a provider in Ozeki AI Gateway.
How to create a Vercel AI Gateway API key to use in Ozeki AI Gateway
vLLM is a high-performance inference engine for running large language models on your own hardware. This guide explains how to enable API key authentication on a self-hosted vLLM server and register it as a provider in Ozeki AI Gateway.
How to create a vLLM API key to use in Ozeki AI Gateway
xAI develops the Grok series of language models, available through an OpenAI-compatible developer API. This guide walks you through generating an API key in the xAI console and configuring it as a provider in Ozeki AI Gateway.
How to create a xAI API key to use in Ozeki AI Gateway
Xinference is a self-hosted inference platform for running open-source models locally with optional API key authentication. This guide covers enabling authentication in Xinference and connecting a local instance to Ozeki AI Gateway as a provider.
How to create a Xinference API key to use in Ozeki AI Gateway
LM Studio is a desktop application for running large language models locally without any cloud dependency. This guide shows how to download a model, start the built-in OpenAI-compatible API server, and connect it to Ozeki AI Gateway as a provider for fully local, private AI inference.
How to use LM Studio with Ozeki AI Gateway
Clarifai provides access to a wide range of hosted AI models through an OpenAI-compatible API. This guide walks you through generating a personal access token in the Clarifai console and registering it as a provider in Ozeki AI Gateway.
How to create a Clarifai API key to use in Ozeki AI Gateway
Scaleway is a European cloud provider offering managed AI inference for open-source language models. This guide covers generating an API key through the Scaleway IAM console and setting it up as a provider in Ozeki AI Gateway.
How to create a Scaleway API key to use in Ozeki AI Gateway