ModelRefs / Inference Endpoint — AI Glossary

Inference Endpoint — AI Glossary

A deployed API endpoint that serves a specific model for real-time or batch inference requests. Self-hosted stacks use vLLM or TGI behind a reverse proxy.

Overview

Inference endpoints abstract the serving infrastructure — GPU allocation, autoscaling, load balancing. Major providers: OpenAI, Anthropic, Google Vertex, AWS Bedrock, Azure AI, Replicate, Together.ai. Self-hosted stacks use vLLM or TGI behind a reverse proxy.

Reference details

Topicinfrastructure
Last reviewed2026-06-24

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Inference Endpoint — AI Glossary.

Frequently asked questions

What is Inference Endpoint?

A deployed API endpoint that serves a specific model for real-time or batch inference requests.

What concepts are related to Inference Endpoint?

Closely related concepts include vllm, model gateway, inference.