Which model types are supported?

Azion AI Inference supports model categories including LLMs, VLMs, embeddings, and rerankers. Browse all models

How do I use AI Inference in my application?

You can call AI Inference directly from Functions with the API pattern const response = await Azion.AI.run(model, input) and integrate it into your existing request flow.

Is Azion AI compatible with OpenAI APIs and SDKs?

Yes. Azion AI Inference provides OpenAI-compatible endpoints, so migration typically requires endpoint and credential updates instead of full rewrites.

How do I implement RAG and semantic search?

Use AI Inference with SQL Database vector search to store embeddings, retrieve relevant context, and build retrieval-augmented generation flows.

Can I fine-tune models with proprietary data?

Yes. You can apply LoRA fine-tuning to pre-trained models to adapt them and improve task accuracy for domain-specific workloads.

What if the model I need is not available?

Azion is constantly expanding model support. If you need a specific model that's not yet available, open a Support ticket or submit feedback through the Azion Console. Each request is evaluated based on technical feasibility and demand.

What is the difference between training and inference?

Training teaches a model with data and is typically resource-intensive. Inference is running the trained model to generate predictions or responses, which is the phase handled by Azion AI Inference.

How can I monitor AI application behavior in production?

You can monitor requests, latency, and runtime behavior with Real-Time Metrics, Real-Time Events, and GraphQL APIs for operational visibility.

Do I need to manage servers or clusters for scaling?

No. AI workloads scale automatically on Azion infrastructure, including scale-to-zero behavior and usage-based pricing.

Can AI be used for autonomous security use cases?

Yes. You can deploy AI agents to analyze content in real time, detect malicious patterns, and trigger automated mitigation workflows.

Run AI Inference globally to power smarter applications | Azion

Global inference on GPUs

Run real-time serverless inference on GPUs across hundreds of locations with median latency under 30 ms. No infra to manage.

OpenAI-compatible API

Migrate and integrate AI features quickly using OpenAI-compatible endpoints and SDKs. Just swap the endpoint.

Real-time decisioning with AI agents

Run ReAct-style AI agents on a distributed architecture to reason over context, call tools, and respond in real time.

RAG with SQL vector search

Integrate AI Inference with SQL Database vector search to power semantic retrieval and hybrid search.

Observability built for AI

Track behavior and performance with Real-Time Metrics, Real-Time Events, and GraphQL APIs.

AI-powered security workflows

Build autonomous security agents to detect abuse and mitigate threats before origin impact. Or deploy a pre-built one instantly.

AI agents

Run AI agents that call your APIs and tools, keep state, and hand off to a person for approval.

Docs

Remote MCP servers

Deploy MCP servers that let AI agents use your services, protected by authentication and rate limits.

Docs

AI features for existing applications

Add summarization, classification, or moderation to your applications, with no GPU infrastructure to run.

Docs

//Your stack, your way

Quick start with templates

Build faster with pre-built applications and starter kits for common use cases. Deploy complete projects in seconds with popular frameworks.

Deploy now

AI Inference Starter KitAI app with no origin dependency.

Deploy now

Function Starter KitAI app with OpenAI-compatible APIs.

Deploy now

LangGraph AI Agent BoilerplateAI agent with RAG, built with LangGraph.

Deploy now

SQL Database Starter KitJavaScript CRUD project on SQL Database.

Deploy now

TiDB Starter Kit with Drizzle ORMTiDB database app with Drizzle ORM.

Deploy now

Cosmic + Simple Next.js BlogNext.js blog managed in Cosmic.

Deploy now

Compatible With Your Stack

OpenAI
Anthropic
Groq
AWS
Google Cloud
Azure

One of the best CDN and WAF solutions I've ever used. Easy to implement and integrate, with speed and low latency that make a real difference for our customers.

Julian H.IT OPS, SRE & SEC Manager at Dafiti Group

See success stories

Ismael AguilarInformation Security Manager at Zoop

Marcelo PachecoDevOps Specialist at Contabilizei

GPA — Allan MonteiroCISO & Head of Technology

One of the best CDN and WAF solutions I've ever used. Easy to implement and integrate, with speed and low latency that make a real difference for our customers.

Julian H.IT OPS, SRE & SEC Manager at Dafiti Group

See success stories

Serverless AI-native primitives for autonomous workloads

//Region: Earth.

Distributed infrastructure that stays up when others go down

Built around your users. Distributed around your data.

100+ data centers
100+ Tbps throughput
Instant scale, automatic routing & failover
30 ms median latency
Always-on DDoS protection
PCI DSS and SOC 2/3 compliant

Global resilience beyond anycast. Azion's software-defined global router steers traffic around failures and network degradation faster than BGP can reconverge. Always-on DDoS protection across 100+ data centers worldwide.

Low latency everywhere. Compute, AI, databases, and security run across all data centers, close to your users, keeping median global latency under 30 ms, with a built-in CDN and tiered caching for every app.

Zero-ops autoscaling and failover. Absorbs any traffic spike with no cold starts, instantly scaling from zero to millions. No capacity planning, no provisioning. Scale-to-zero with no idle costs: you pay only for what you run.

Recognized as a market leader

Recognized as a Leader in CDN, Web Security, and DDoS Protection, and a High Performer in Cloud Security, WAF, Bot Detection and Mitigation, SSL & TLS Certificate Tools, and API Security Tools.
G2 Spring 2026 Reports
Recognized as a Leader in CDN and a High Performer in Web Security, DDoS Protection, WAF, Bot Detection and Mitigation, SSL & TLS Certificate Tools, and DNS Security Solutions.
G2 Winter 2026 Reports
Named a Leader and the only platform purpose-built for the edge, whose capabilities meet all key criteria in the report.
GigaOm Radar for Edge Platforms
Awarded in the Edge Serverless Computing category and recognized for consistently exceeding its customers' performance expectations.
2023 North American New Product Innovation Award

Recognized as a Leader in CDN, Web Security, and DDoS Protection, and a High Performer in Cloud Security, WAF, Bot Detection and Mitigation, SSL & TLS Certificate Tools, and API Security Tools.
G2 Spring 2026 Reports
Recognized as a Leader in CDN and a High Performer in Web Security, DDoS Protection, WAF, Bot Detection and Mitigation, SSL & TLS Certificate Tools, and DNS Security Solutions.
G2 Winter 2026 Reports
Named a Leader and the only platform purpose-built for the edge, whose capabilities meet all key criteria in the report.
GigaOm Radar for Edge Platforms
Awarded in the Edge Serverless Computing category and recognized for consistently exceeding its customers' performance expectations.
2023 North American New Product Innovation Award

Frequently asked questions

//Build

Build once.Run everywhere.

Start free

Get a faster path to launch, lower latency, and less infrastructure overhead.

Talk to a specialist