Kong AI Gateway and Azure API Management side by side
| Kong AI Gateway | Azure API Management | |
|---|---|---|
| What it is | AI gateway on Kong Gateway, managed in Kong Konnect or self-hosted | AI gateway capabilities of API Management's existing gateway; not a separate offering |
| Price | Plus from $25 a month plus usage: $100 a month per model (up to 5), 1 million requests included, $200 per additional million; Enterprise custom, billed annually | By tier: Consumption per operation (1 million included); Basic v2 includes 10 million requests a month, Standard v2 50 million |
| Model APIs | The providers you configure with your own keys | OpenAI Chat Completions and Responses, Anthropic Messages (v2 tiers) and Vertex AI; a unified model API in preview |
| Token limits | AI Rate Limiting Advanced: an Enterprise plugin, an add-on on Plus | llm-token-limit: tokens per minute or a quota per hour, day, week, month or year on any counter key |
| Semantic caching | AI Semantic Cache: Enterprise plugin, add-on on Plus | With Azure Managed Redis or a RediSearch-compatible cache |
| Load balancing | AI Proxy Advanced: Enterprise plugin, add-on on Plus | Round-robin, weighted, priority and session-aware, with a circuit breaker |
| Processing in Europe | EU Konnect geo for the control plane; model processing depends on each provider | The Azure regions you deploy to, in front of backends you deploy |
| Single sign-on | Enterprise only | Microsoft Entra ID for the developer portal |
| Audit and logs | Audit logs on Enterprise only | Prompts, completions and token metrics to Azure Monitor and Application Insights |
| Billing | Plus monthly by card in USD; Enterprise by invoice or PO | On your Azure bill |
Where they differ most
Where the AI features sit
Azure's token limits, semantic caching, load balancing and content safety apply to all API Management tiers, with Anthropic Messages on v2. Kong's advanced AI plugins are included on Enterprise and an add-on on Plus.
How you pay
Kong Plus charges $100 a month per model, up to 5, plus requests. API Management is priced by tier and unit on your Azure bill.
Identity
Kong says SSO and audit logs are only available with Enterprise. API Management signs developers in to its portal with Microsoft Entra ID.
Choose Kong AI Gateway or Azure API Management
Choose Kong AI Gateway if
- Kong already fronts your APIs across several clouds.
- You are buying Kong Enterprise, which includes the advanced AI plugins.
- You want a managed control plane in Konnect's EU geo.
Choose Azure API Management if
- Your company runs on Azure and already operates API Management.
- Your models are deployments you own in Microsoft Foundry, Bedrock or Vertex AI.
- Token quotas per app are enough, and spend belongs on your Azure bill.
A third option for companies
Both gateways leave you holding a contract with every model provider and running the policies yourself. Standard Compute is a managed gateway that supplies Claude, GPT, Gemini and open models itself, sends each step to the cheapest model that can do it, and lets your people sign in with their Microsoft work accounts.
Cost per step
Each step goes to the cheapest model that can do it and the cheapest provider fast enough to serve it.
Models
Claude, GPT and Gemini alongside open models such as GLM, DeepSeek, MiniMax and Kimi, through one API.
Processing in Europe
A Europe rule per company, team or key: every request, including retries and fallbacks, is served only by approved European inference endpoints, or refused before your prompt is sent.
Zero data retention
Required per company, team or key, and Standard Compute never trains on your prompts or outputs.
Single sign-on
Microsoft Entra ID or any SAML provider, and Claude Desktop and Claude Code sign-in with a Microsoft work account.
Budgets
A fixed monthly budget per person and app that never overruns, and spending caps per key and for the whole company.
Allow-lists
Approved providers per company, team or key, and approved models per key. Fallbacks never route around them.
Audit log
Admin changes with before and after values, and a 12-month export of every request's model, provider and region rule.
Sign our Data Processing Agreement in the dashboard, and see every sub-processor with its purpose and location.
Create a company workspaceTalk to usor write to contact@standardcompute.com
Questions
Is Azure API Management an AI gateway?
Microsoft describes the AI gateway as a set of capabilities of API Management's existing gateway, in all tiers: token limits, semantic caching, load balancing with a circuit breaker, content safety and logging of prompts and completions.
How is Kong AI Gateway priced?
Kong Plus starts at $25 a month plus usage: $100 a month per model, up to 5 models, with 1 million requests included and $200 per additional million. Enterprise is custom and billed annually.
Does Kong AI Gateway include SSO?
Kong says SSO and audit logs are only available with Enterprise.
Can API Management route Claude?
Microsoft lists the Anthropic Messages API among supported schemas in the v2 tiers, for models you deploy in Microsoft Foundry or providers such as Amazon Bedrock.
Is there a gateway that includes the models and the controls?
Standard Compute is one API for Claude, GPT, Gemini and open models, with a Europe rule, zero data retention, Microsoft Entra sign-in, budgets per key and for the company, allow-lists and an audit log.
Sources (checked 18 November 2026)
- Kong pricingkonghq.com
- Kong AI Gatewaydeveloper.konghq.com
- Kong AI Rate Limiting Advanced plugindeveloper.konghq.com
- Kong Konnect geosdeveloper.konghq.com
- Microsoft Learn: AI gateway capabilities in Azure API Managementlearn.microsoft.com
- Azure API Management pricingazure.microsoft.com
- Microsoft Learn: developer portal sign-in with Microsoft Entra IDlearn.microsoft.com