Sold by: Vercel
Deployed on AWS
Robustly access hundreds of AI models through a centralized interface and ship with ease.
4.7
Overview
The AI Gateway provides a unified API to access hundreds of models through a single endpoint. It gives you the ability to set budgets, monitor usage, load-balance requests, and manage fallbacks.
The design allows it to work seamlessly with AI SDK 5, OpenAI SDK, or your preferred framework.
Key features include:
- Unified API: helps you switch between providers and models with minimal code changes
- High Reliability: automatically retries requests to other providers if one fails
- Embeddings Support: generate vector embeddings for search, retrieval, and other tasks
- Spend Monitoring: monitor your spending across different providers
Highlights
- Unified API: helps you switch between providers and models with minimal code changes
- High Reliability: automatically retries requests to other providers if one fails
- Spend Monitoring: monitor your spending across different providers
Details
Sold by
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
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 the duration and terms of your contract with the vendor, and additional usage. You pay upfront or in installments according to your contract terms with the vendor. This entitles you to a specified quantity of use for the contract duration. Usage-based pricing is in effect for overages or additional usage not covered in the contract. These charges are applied on top of the contract price. If you choose not to renew or replace your contract before the contract end date, access to your entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
AI Gateway credit | Contact Us for Private Offer Pricing | $1,000,000.00 |
Dimension | Cost/unit |
|---|---|
On-demand credit | $0.01 |
Dimensions summary
AI Gateway sells through credits that you draw down as you use the service. Both dimensions bill in credit units. On-demand credit lets you top up and pay per request as usage occurs. AI Gateway credit is set through a private offer, so you contact the vendor for negotiated pricing. This suits buyers who want committed pricing tied to their AWS cloud commitment. You use credits to route requests across many AI models through one endpoint, with usage drawn down per request.
Top-of-mind questions for buyers
A credit is prepaid value drawn down per request. You pay the upstream provider's token price with no markup added. Each request deducts credits based on the tokens used by the model you route to. Token pricing varies by model and provider.
On-demand credit lets you top up and draw down per request as usage happens, with no upfront commitment. AI Gateway credit is arranged through a private offer for negotiated pricing. Both meter the same per-request token usage; the difference is how you purchase and commit.
You pay the token price for the model that actually serves your request. If a provider degrades, the Gateway routes to the same model on another provider. You draw down credits for whichever provider fulfills the request, with no added platform fee.
vercel.com
Helpful?
Vendor refund policy
Please refer to Vercel Terms of Service: https://vercel.com/legal/terms or reach out to awsmarketplace@vercel.com
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
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
Please reach out to awsmarketplace@vercel.com
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
The Netskope AI Gateway is a software layer designed to act as a gateway to intercept and secure traffic between AI agents and AI models (LLMs) esp, the east-west traffic that does not go through Netskope Edge.
AI Gateway provides a unified, high-performance access layer for multiple AI models. Use one API to invoke LLMs, image, video, and TTS models with global acceleration and redundancy. It streamlines integration while offering centralized management and enterprise-grade stability worldwide.
This product has charges associated with it for deployment, configuration, and ongoing support. Self-hosted OpenAI-compatible API gateway for Claude Sonnet 4, Opus 4.5, Haiku 4.5. Connect Cursor, Windsurf, Continue, or any OpenAI-compatible tool. No per-token costs, powered by Kiro subscription. Pre-configured, launch in 5 minutes.
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 product has charges associated with it for the provision and deployment of the application and AMI support.
Customer reviews
umair d.
The Absolute Best Deployment and Hosting Platform for Modern React Applications
Reviewed on Aug 11, 2026
Review provided by G2
What do you like best about the product?
Vercel's automatic deployment from GitHub is completely magical. It provides ultra-fast global CDN edge hosting, which gives my React templates a perfect 100/100 Google Lighthouse speed and SEO score without any manual server configuration.
What do you dislike about the product?
While the free hobby tier is amazing, the pricing gap skips heavily when transitioning to the pro plan for smaller freelance agencies. Also, managing complex serverless functions can sometimes be tricky for pure frontend developers.
What problems is the product solving and how is that benefiting you?
It completely solves the hassle of complex server hosting and SSL configuration. It allows me to instantly push my code live to production with zero configuration, making client project showcasing extremely efficient.
Praveen V.
Easy Git deployments with shareable instant preview URLs - no engineering help needed
Reviewed on Aug 08, 2026
Review provided by G2
What do you like best about the product?
Git deployments that I don't need to configure. Instant preview URLs that I can share with anyone in the team.
What do you dislike about the product?
The pricing is a bit unpredictable. The Pro plan is $20/seat/month, but that's just a credit wallet. High chances of exceeding the 1 TB included in this plan leading to paying way higher than expected.
What problems is the product solving and how is that benefiting you?
Preview URLs let me spin up mockup pages, create shareable links, and get them reviewed from the team internally. I don't need engineering help for this.
Hospital & Health Care
An Intuitive, Beginner-Friendly Fix for Hosting with Vercel
Reviewed on Aug 06, 2026
Review provided by G2
What do you like best about the product?
Serves as an easy solve to the hosting problem and great for beginners. When I was making websites on my own back in the day, I would use the vercel supabase stack, which is intuitive and simple in the age of nontechnical literate coders and vibe coders
What do you dislike about the product?
Not much I don’t like about vercel. I suppose it doesn’t give as much precision as a service like webflow, but, as I said, great for beginners.
What problems is the product solving and how is that benefiting you?
It solves the problem of wanting a simple and familiar interface for beginners at a budget
Tejas T.
Fast Git Deploys, Global Low-Latency Edge, and Clear Logs
Reviewed on Jul 22, 2026
Review provided by G2
What do you like best about the product?
Zero-config deploys from Git, preview URLs per PR speed up review cycles a lot. Edge network keeps latency low for our dashboard globally. Build times are fast, logs are clear when something breaks. Analytics built-in saves us a separate tool. Free tier's generous early on.
What do you dislike about the product?
Costs climb fast once you scale past hobby usage, especially with serverless function invocations. Cold starts on edge functions can spike latency unpredictably. Build minutes get eaten quickly on larger monorepos. Support's slow unless you're on enterprise. Some config feels locked-in to their platform
What problems is the product solving and how is that benefiting you?
We were manually managing deploys and staging environments, which slowed releases and caused config drift. Now every PR gets an isolated preview automatically, so QA and stakeholders test real builds before merge. Deploy pipeline that used to take hours now happens in minutes.
Aashu J.
Vercel Made Me Publish My College Project Instead of Keeping It on My Laptop
Reviewed on Jul 21, 2026
Review provided by G2
What do you like best about the product?
I used Vercel to deploy a college admission help portal that I built while learning Node.js during my first year of B.Tech. What I liked most was that I stopped treating deployment as the final step that only experienced developers could do. At first, I kept testing everything on my local machine because I thought hosting would be confusing. After using the GitHub integration, Deployment Dashboard, and Preview Deployments, I started putting every working version online instead of waiting until the project felt "complete." Seeing the live link made me notice small issues that I never caught while running it locally. The dashboard is simple enough that I can find my recent deployment without clicking through too many pages. My deployments have been reliable for the type of student projects I build. Since I only needed basic hosting, the free plan has been more than enough, which is important as a student. The onboarding was straightforward, and I had my first project online without spending much time learning the platform. I haven't relied much on the AI features, but the suggestions were useful once when I was trying to understand why my deployment wasn't updating after a code change. The best helpful thing was that I became comfortable publishing my work early instead of waiting until I thought it was perfect.
What do you dislike about the product?
When a deployment failed because of a small mistake in my Node.js project, I had to spend some time reading the logs before I understood the actual reason. As a beginner, the messages were sometimes less clear than I expected. Also, after creating multiple practice deployments, the project list became a little crowded.
What problems is the product solving and how is that benefiting you?
Earlier, I would show my college projects by sending screenshots or running them on my own laptop. Now I simply share a live link with classmates so they can try the project themselves. As a result, I receive more useful feedback because people interact with the actual application instead of looking at images or recorded videos.