Sold by: Code Creator
Deployed on AWS
Self-hosted AI gateway for centralized LLM provider routing, virtual key management, and spend tracking. Deploy on your own AWS instance with automated first-boot setup.
Overview
AI Developer API Gateway by Code Creator
Launch a self-hosted AI API gateway on your AWS account in minutes. AI Developer API Gateway by Code Creator gives developers, platform teams, startups, agencies, and businesses a centralized, OpenAI-compatible gateway layer - eliminating the need to wire every application directly to a single AI provider.
The Problem This Solves
Teams building AI-powered applications often connect each app directly to a provider API, creating scattered key management, no centralized spend visibility, and no unified routing layer. As projects scale, this approach becomes difficult to manage and secure.
With this AMI, you launch a preconfigured gateway server in your own AWS account that centralizes provider routing, virtual key management, spend tracking, and OpenAI-compatible API access - all under your control.
How It Works
- Launch the AMI from AWS Marketplace into your EC2 environment
- First-boot automation runs automatically - generating fresh, customer-specific credentials, detecting your public IP, starting the full Docker stack, and creating a FIRST_LOGIN guide
- Access the Admin UI and API through your browser or any OpenAI-compatible client
- Add your own provider keys for OpenAI or other supported providers to begin routing AI API traffic through your gateway
You bring your own provider API keys. This gives you full control over provider accounts, budgets, and application access while benefiting from a preconfigured, centralized gateway environment.
Key Capabilities
- LiteLLM Admin UI - Manage model routes, virtual keys, and spend visibility from a web dashboard
- OpenAI-Compatible API Base - Use as a drop-in replacement for OpenAI endpoints across your applications
- Virtual Key Management - Issue and manage virtual API keys for teams, projects, or individual applications
- Provider Key Onboarding - Add keys from OpenAI and other supported providers after launch
- Secure Generated Master Key - Fresh credentials created automatically at first boot
- PostgreSQL-Backed Storage - Key management and configuration data persisted in PostgreSQL
- Redis-Backed Caching - Improve response performance with integrated Redis caching
- Nginx Front Door - LiteLLM runs behind Nginx and is bound internally to localhost, limiting direct exposure
- Developer Examples and Helper Commands - Get started quickly with included code samples and CLI utilities
- First Login Documentation - A generated FIRST_LOGIN guide walks you through initial setup
Use Case: Software Agency Managing Multiple Client Projects
A software agency building AI-powered features for multiple clients can use this gateway as a central routing layer. Instead of managing separate provider API keys and direct integrations for each client project, the agency launches one gateway instance, onboards provider keys per client, issues virtual keys scoped to each project, and monitors spend across all engagements from a single Admin UI. This centralizes key management, simplifies billing visibility, and provides a consistent OpenAI-compatible API base that every client project connects to.
Use Case: Complementing Private AI Chat Deployments
This product - also known as Private AI Developer Gateway by Code Creator - is designed to complement private AI chat products. While chat-focused products serve end users, this gateway focuses on the developer API infrastructure layer: testing, development, application integration, virtual key management, and provider key onboarding for the teams building those applications.
Built on a Production-Ready Stack
The AMI is built on Ubuntu 24.04 and includes LiteLLM, PostgreSQL, Redis, Docker, Docker Compose, and Nginx - all preconfigured and orchestrated through Docker Compose. The first-boot automation handles credential generation, IP detection, stack startup, and documentation creation so you can move from launch to a working gateway quickly.
Who This Is For
- AI application developers who need a centralized API base for multiple AI-powered projects
- Internal engineering teams standardizing how their organization accesses AI provider APIs
- Software agencies managing provider keys and spend across multiple client engagements
- AI prototyping teams who want fast iteration without reconfiguring provider connections per project
- Businesses seeking a faster path to a centralized, self-hosted AI API gateway on AWS
What You Are Paying For
Code Creator charges cover the integrated AI API gateway stack, automated first-boot deployment, customer credential generation, PostgreSQL and Redis integration, Nginx configuration, public IP onboarding, virtual key workflows, developer examples, and AWS Marketplace-ready AMI engineering. Standard AWS infrastructure costs for your EC2 instance, storage, and network apply separately.
Highlights
- Centralize AI API access from a single self-hosted gateway instead of wiring each application directly to individual LLM providers. The gateway supports OpenAI-compatible endpoints, provider routing, and consolidated spend tracking so teams can monitor and control AI usage across projects from one place. Run everything within your own AWS account for full data control and network isolation.
- Manage developer access securely with virtual keys that let you assign scoped credentials to individual team members or applications without sharing raw provider API keys. The LiteLLM Admin UI provides browser-based visibility into model routes, key usage, and spend data, giving administrators a single dashboard for governance and cost awareness across all connected AI providers.
- First-boot automation handles the operational setup that would otherwise require manual configuration. On initial launch, the server generates fresh credentials, creates a customer-specific access guide, detects the public IP address, and starts the full Docker stack including LiteLLM, PostgreSQL, Redis, and Nginx - so the gateway is ready for browser and API access without manual provisioning steps.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.03 |
t3.xlarge | $0.03 |
m6i.xlarge | $0.03 |
c7i.4xlarge | $0.03 |
c7i.xlarge | $0.03 |
c7i.2xlarge | $0.03 |
c7i.large | $0.03 |
t3.2xlarge | $0.03 |
m6i.2xlarge | $0.03 |
t3.medium | $0.03 |
Dimensions summary
You pay by the hour based on the AWS EC2 instance type you run. All 12 options bill the same software on different instance sizes. The t3 family (medium, large, xlarge, 2xlarge) offers general-purpose capacity. The m6i family (large, xlarge, 2xlarge, 4xlarge) adds more balanced compute and memory. The c7i family (large, xlarge, 2xlarge, 4xlarge) targets compute-heavy workloads. Larger sizes within each family provide more CPU and memory. Your cost scales with the instance size you choose and the hours you run it. You also pay standard AWS infrastructure charges separately.
Top-of-mind questions for buyers
One unit is one running EC2 instance of that type, billed per hour. The software runs on your chosen instance size. Each active instance-hour counts separately. If you run two instances of the same type, you pay for both. The rate reflects the instance size you select.
Software charges meter running instance-hours only. A fully stopped instance does not accrue software fees. Stopped or paused instances may still incur standard AWS charges for attached storage, but the software licence bills active runtime. Charges resume once you restart the instance.
The billing method stays the same across all 12 instance types. You always pay per running hour. Choosing a larger size within the t3, m6i, or c7i family raises the hourly rate. Switching families changes the CPU-to-memory balance. Your cost tracks the instance you run and the hours it runs.
www.codecreator.com
Helpful?
Vendor refund policy
No contracts. We do not currently support refunds, but you can cancel at any time.
Custom pricing options
Request a private offer to receive a custom quote.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
AI Developer API Gateway by Code Creator is a ready to launch, self hosted AI API control plane for developers, teams, agencies, and businesses. It centralizes OpenAI compatible AI requests behind an AWS instance you control, with LiteLLM for provider routing, virtual key management, spend-aware workflows, and developer integrations.
Additional details
Resources
Vendor resources
Support
Vendor support
For support inquiries related to the AI Developer API Gateway, contact Code Creator by email at info@codecreator.com .
After launching the AMI, a customer-specific access guide is generated on the server during first-boot automation, which includes credentials and initial configuration details to help you get started.
For additional technical reference, the following external documentation is available:
- LiteLLM Documentation: https://docs.litellm.ai/docs/
- Virtual Key Management: https://docs.litellm.ai/docs/proxy/virtual_keys
- OpenAI API Quickstart:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Launch a self hosted Kong API Gateway and AI Gateway on Ubuntu 26.04 LTS with Docker Compose, PostgreSQL, a public IP landing page, a working demo route, and an AI Gateway starter helper for OpenAI compatible traffic. Built for developers and teams that want fast API routing, testing, and AI gateway workflows inside their own AWS account. This is a repackaged open source software product wherein additional charges apply for Code Creator integration of Kong Gateway, PostgreSQL and Docker Compose, automated first boot public IP configuration, working API demo route, AI Gateway setup tooling, backup and configuration helpers, security configuration, and AWS Marketplace AMI engineering.
Deploy a private AI chat and OpenAI-compatible API gateway on your own AWS infrastructure. Pre-integrated Open WebUI, Ollama, and LiteLLM with automated first-boot setup on Ubuntu instance.
This is a repackaged open source software product wherein additional charges apply for Code Creator integration of Dify and Langfuse, Docker based deployment, private AWS runtime configuration, browser based administrator onboarding, model provider connectivity, and integrated AI observability for traces metrics evaluations latency and cost. Build and monitor AI applications agents and workflows inside your own AWS account. Self hosted Dify and Langfuse AI app studio on Ubuntu that lets you build AI workflows and agents in the browser and observe every request in your own AWS account using your own LLM provider keys.
Headroom AI Context Compression Gateway by Code Creator provides a private Ubuntu based AI context optimization gateway for developers, AI agents, coding tools, and LLM applications. It includes Headroom, Nginx, public IP onboarding, first boot IP refresh, health checks, helper commands, and examples for OpenAI compatible and Anthropic compatible clients. This is a repackaged open source software product wherein additional charges apply for Code Creator integration of Headroom and Nginx, automated first boot public IP configuration, health and service checks, client examples, operational helper commands, security configuration, and AWS Marketplace AMI engineering.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.