Sold by: Meetrix.io
Deployed on AWS
AWS Free Tier
9Router is a self-hosted LLM gateway that connects Claude Code, Codex, Cursor, Cline, Copilot, and other AI coding tools to 40+ model providers through a single OpenAI-compatible endpoint. It translates request formats across OpenAI, Claude, and Gemini APIs, tracks quota, auto-refreshes tokens, and falls back from subscription to cheap to free providers so requests never stop. A built-in RTK token saver compresses tool output to cut input token usage by 20 to 40 percent. This AWS Marketplace AMI deploys a pre-configured 9Router instance on EC2 with Docker, an SSE-tuned nginx reverse proxy, automatic Let's Encrypt SSL, and optional daily SQLite backups to S3, giving developers and engineering teams a unified AI model router they fully control.
Overview
9Router is a self-hosted LLM gateway and smart routing proxy that sits between your AI coding tools and dozens of model providers. It exposes a single OpenAI-compatible endpoint, translates request and response formats across OpenAI, Claude, and Gemini APIs, tracks provider quota, auto-refreshes access tokens, and automatically falls back from subscription to low-cost to free providers so your requests never stop. This AWS Marketplace AMI deploys a pre-configured 9Router instance on EC2, giving developers, engineering teams, and SaaS platforms a ready to use AI model router without manual installation or server configuration.
9Router Step by step Installation Guide: https://meetrix.io/blogs/9router-developer-guide/
For custom projects of your choice with personalized support, contact us at https://meetrix.io/contact-us
Single OpenAI-Compatible Endpoint: Point Claude Code, Codex, Cursor, Cline, Copilot, and other CLI tools at one URL and reach 40+ LLM providers without changing your workflow.
Automatic Provider Fallback: 9Router routes each request subscription first, then low-cost, then free, so rate limits or outages on one provider never stop your work.
Cross-API Format Translation: Requests and responses are translated between OpenAI, Claude, and Gemini formats, so any client works with any provider.
RTK Token Saver: A built-in compression layer shrinks tool output before it reaches the model, cutting input token usage by 20 to 40 percent.
Quota Tracking and Token Refresh: 9Router tracks usage per provider and auto-refreshes access tokens so credentials stay valid without manual intervention.
Secure Streaming Proxy: An nginx reverse proxy tuned for SSE handles HTTP and HTTPS with automatic Let's Encrypt SSL via the Route53 DNS challenge.
Persistent Data and Backups: SQLite data lives on a persistent gp3 EBS volume with an optional daily gzipped backup to S3.
Pre-Hardened Base Image: The AMI ships on a hardened Ubuntu base with Docker and Docker Compose preinstalled for a fast, secure first boot.
Version: 0.5.59
Operating System: Ubuntu 26.04
9Router gives developers and engineering teams a self-hosted, vendor-neutral LLM gateway they can deploy in minutes and fully control on their own AWS infrastructure. Get started with the step by step installation guide: https://meetrix.io/blogs/9router-developer-guide/
Highlights
- Unified LLM Gateway: Connect your AI coding tools to 40+ model providers through a single OpenAI-compatible endpoint, with request and response formats translated between provider APIs automatically.
- Automatic Fallback Routing: 9Router routes each request from subscription to low-cost to free providers, so rate limits and provider outages never interrupt your work.
- Lower Token Costs: The built-in RTK token saver compresses tool output before it reaches the model, cutting input token usage by 20 to 40 percent.
Details
Sold by
Categories
Delivery method
Delivery option
9Router Deployment with Single EC2 Instance
Latest version
Operating system
Ubuntu 26.04
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.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Cost/hour |
|---|---|
t2.micro | $0.001 |
t2.small | $0.019 |
t2.large | $0.024 |
t2.xlarge | $0.029 |
t2.medium | $0.024 |
t3a.large | $0.024 |
t3a.xlarge | $0.029 |
t3.large | $0.024 |
t3.xlarge | $0.029 |
t3.small | $0.019 |
Dimensions summary
You pay by the hour for the EC2 instance size you run the 9Router software on. The software price is the same across all options; your cost changes with the compute you pick. Choices span general-purpose burstable families (t2, t3, t3a), balanced families (m4, m5, m5a, m6a, m6i, m7i, m7a), compute-optimized families (c5, c5a, c6a), and memory-optimized families (r5, r5a, r6a, r6i). Within each family, larger sizes cost more per hour. The vendor suggests t3a.small for a single user or small team. Larger sizes suit heavier concurrent traffic through the proxy.
Top-of-mind questions for buyers
The hourly charge covers the running EC2 instance size you launch. The software price stays the same across all sizes. When you stop the instance, software charges stop. The Elastic IP and EBS data volume are retained while stopped, so underlying AWS storage fees may still apply.
No. You pay only for the EC2 instance size you run. You can connect one provider or many, and point any number of coding tools at the single endpoint. The provider connections and tool usage do not add to your Marketplace hourly charge.
The vendor recommends t3a.small for a single user or small team. If concurrent traffic through the proxy grows, pick a larger size, which costs more per hour. To change size, back up your data, remove the deployment, and relaunch with the new instance type.
meetrix.io
Helpful?
Vendor refund policy
We do not currently support refunds, but you can cancel at any time.
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
9Router Deployment with Single EC2 Instance
This deployment launches 9Router within a dedicated VPC on a single EC2 instance, providing a ready to use environment for LLM gateway and multi-provider routing workflows. The AMI is preinstalled and configured, allowing users to open the dashboard, connect one or more model providers, and point their AI coding tools at a single OpenAI-compatible endpoint immediately after launch. An nginx reverse proxy tuned for SSE streaming handles HTTP and HTTPS traffic, with SSL issued automatically through Let's Encrypt using the Route53 DNS challenge. SQLite data is stored on a persistent gp3 EBS volume, with an optional daily gzipped backup to an S3 bucket. This architecture is designed for secure request routing, simplified management, and fast deployment.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
First Release
Additional details
Usage instructions
Click the "Continue to Subscribe" button. After subscribing, you will need to accept the terms and conditions. Click on "Accept Terms" to proceed. Please wait for a few minutes while the processing takes place. Once it's completed, click on "Continue to Configuration".
IAM Role is set up and configured with the necessary permissions to assume the role for the 9Router service. The IAM Policy is created and responsible for access Route53 and create Letsencrypt SSL certificates and backing up data to the S3 bucket.
Access the application via a browser at http://<your domain name> or http://<Public IPv4 address>. Product will try to create SSL certificate when its deploying, if domain hosted on route53. If the automatic SSL creation unsuccessful then you have to point domain name into server ip, ssh into server and run /root/certificate_generate_standalone.sh. Admin email using for SSL generation.
Resources
Vendor resources
Support
Vendor support
Please contact us through aws@meetrix.io . Please allow up to 12 hours for our support team to address your request.
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
REQUIRES PRIVATE OFFER
To purchase LiteLLM Enterprise Self-Hosted, please reach out to sales@berri.ai for a Private Offer.
LiteLLM is an OpenAI compatible Proxy Server (LLM Gateway) to call 2,000+ LLM APIs using the OpenAI format Bedrock, Huggingface, VertexAI, TogetherAI, Azure OpenAI, OpenAI, etc. Get started with Opensource LiteLLM here: https://github.com/BerriAI/litellm (40,000+ Github Stars)
MultiCortex HPC with amazon-ssm-agent (High Performance Computing) based on openSUSE and works with models without needing internet access.
Private AI inference gateway with Open WebUI, Ollama, LiteLLM, local CPU model serving, and an OpenAI compatible API endpoint on Ubuntu 24.04. This is a repackaged open source software product wherein additional charges apply for Code Creator integration of Open WebUI, Ollama, LiteLLM, PostgreSQL, Redis and Nginx, automated first boot configuration, local model serving, API gateway setup, helper tooling, and AWS Marketplace AMI engineering.
This product has charges associated with it for support from the seller. Built on openSUSE Linux, this product provides private AI using the Qwen 2.5 model with 0.5 billion parameters. MultiCortex HPC (High-Performance Computing) allows you to boost your AI's response quality. This is a plug-and-play, low-cost product with no token fees.
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.