Turn your existing data & APIs into governed capabilities for AI →

API Learnings

Toolbox

API Evangelist LLC

microsoft-azure-api-management

Azure API Management AI Gateway

The Azure API Management AI gateway is a set of capabilities for managing, securing, scaling, and observing AI backends including Microsoft Foundry and Azure OpenAI deployments, OpenAI-compatible LLM endpoints, MCP servers, and A2A agent APIs. It provides token rate limiting and quotas, semantic caching, load balancing across AI backends, content safety enforcement, and token usage observability through Application Insights.

Documentation GitHub OpenAPI

Documentation

https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities

https://learn.microsoft.com/en-us/azure/api-management/azure-openai-api-from-specification

https://learn.microsoft.com/en-us/azure/api-management/azure-ai-foundry-api

Specifications

openapi/microsoft-azure-api-management-ai-gateway-openapi.yaml

json-ld/microsoft-azure-api-management-ai-gateway-context.jsonld

Schemas & Data

json-schema/ai-gateway-chat-completion-request-schema.json

json-schema/ai-gateway-chat-completion-response-schema.json

json-schema/ai-gateway-completion-request-schema.json

json-schema/ai-gateway-completion-response-schema.json

json-schema/ai-gateway-embedding-request-schema.json

json-schema/ai-gateway-embedding-response-schema.json

json-schema/ai-gateway-mcp-request-schema.json

json-schema/ai-gateway-mcp-response-schema.json

json-structure/ai-gateway-chat-completion-request-structure.json

json-structure/ai-gateway-chat-completion-response-structure.json

json-structure/ai-gateway-completion-request-structure.json

json-structure/ai-gateway-completion-response-structure.json

json-structure/ai-gateway-embedding-request-structure.json

json-structure/ai-gateway-embedding-response-structure.json

json-structure/ai-gateway-mcp-request-structure.json

json-structure/ai-gateway-mcp-response-structure.json

Examples

examples/ai-gateway-chat-completion-request-example.json

examples/ai-gateway-chat-completion-response-example.json

examples/ai-gateway-completion-request-example.json

examples/ai-gateway-completion-response-example.json

examples/ai-gateway-embedding-request-example.json

examples/ai-gateway-embedding-response-example.json

examples/ai-gateway-mcp-request-example.json

examples/ai-gateway-mcp-response-example.json

Other Resources

NaftikoCapability

capabilities/shared/ai-gateway.yaml

OpenAPI

#AI Gateway #Azure OpenAI #LLM #MCP

← Back to A APIs