20 docs tagged with "AI gateway"

View all tags

Adapting AI Middlewares for Responses API

Learn how to configure Traefik Hub AI Gateway middlewares for OpenAI Responses API workloads.

AI Gateway Failover

Configure automatic failover between LLM providers using the Traefik Hub AI Gateway.

Bedrock Mantle

Traefik Hub – Configure the Bedrock Mantle middleware for the AI Gateway.

Chat Completion

Traefik Hub – Configure the Chat Completion middleware for the AI Gateway.

Configure AI Gateway Observability

Traefik Hub – Configure GenAI metrics and trace attributes for the AI Gateway middlewares.

Content Guard

Traefik Hub - Learn how to configure the Content Guard middleware for the AI & API gateway.

Google Agent Platform

Traefik Hub – Configure the Google Agent Platform middleware for the AI Gateway.

IBM Granite Guardian Integration with Traefik Hub AI Gateway LLM Guard Middleware

Complete guide for integrating IBM Granite Guardian models with Traefik Hub AI Gateway LLM Guard middleware for advanced AI content security and topic control.

LLM Guard

Traefik Hub - Learn how to configure the LLM Guard middleware for flexible content security in the AI Gateway.

Messages API

Traefik Hub – Configure the Messages API middleware for the AI Gateway.

Model Context Protocol (MCP)

Traefik Hub - Configure the MCP middleware for secure access control and governance of MCP servers.

Monitor Token Usage and Cache Savings

Track token consumption from streamed and non-streamed AI responses, enable Responses API semantic caching, and measure tokens saved by cache hits.

NVIDIA NIMs Integration with Traefik Hub AI Gateway LLM Guard Middleware

Complete guide for integrating NVIDIA NIMs with Traefik Hub AI Gateway LLM Guard middleware for advanced AI content security and topic control.

Parallel LLM Guard

Traefik Hub - Learn how to configure the Parallel LLM Guard middleware to run multiple LLM guards concurrently in the AI Gateway.

Responses API

Traefik Hub – Configure the Responses API middleware for the AI Gateway.

Semantic Cache

Traefik Hub - Learn how to configure the Semantic Cache middleware for the AI gateway.

Token Rate Limit & Quota

Traefik Hub - Learn how to configure the Token Rate Limit and Quota middlewares for the AI gateway.

Track AI Inference Costs by Team

Use Traefik Hub AI Gateway metrics to attribute LLM token spend by team, visualize costs in Grafana, set budget alerts, and enforce hard spending caps.

Traefik Hub AI Gateway

Traefik Hub - Learn how to configure the AI Gateway.

Using AI Middlewares with Messages API

Learn how to configure Traefik Hub AI Gateway middlewares for Anthropic Messages API workloads.