Question 1

What is Azion AI Inference?

Accepted Answer

Azion AI Inference is a serverless platform for deploying and running AI models on a distributed architecture. It provides an OpenAI-compatible API for easy migration, supports LLMs, VLMs, embeddings, and reranking models, and offers LoRA fine-tuning for domain customization. Scale automatically without GPU management while maintaining low-latency responses globally.

Question 2

Which models can I run?

Accepted Answer

Choose from a catalog of open-source models for text and code generation, vision-language tasks, embeddings, and reranking. The catalog evolves as new models become available, and you can fine-tune supported models with LoRA for your specific domain.

Question 3

Is it compatible with OpenAI API?

Accepted Answer

Yes. AI Inference uses an OpenAI-compatible API format, so you can migrate existing applications by updating the base URL and credentials. Keep your current SDKs and integration patterns—no code rewrite required.

Question 4

Can I fine-tune models?

Accepted Answer

Yes. AI Inference supports LoRA (Low-Rank Adaptation) fine-tuning, allowing you to specialize models for your domain without full retraining. This reduces compute costs while improving accuracy for specific tasks like customer support, code generation, or domain-specific Q&A.

Question 5

How do I build RAG and semantic search?

Accepted Answer

Use AI Inference with SQL Database Vector Search to store embeddings and retrieve relevant context for RAG applications. This built-in vector search means no separate vector database to manage—SQL and vectors in one service.

Question 6

Can I build AI agents and tool-calling workflows?

Accepted Answer

Yes. AI Inference powers agent patterns like ReAct and tool-calling workflows when combined with Applications, Functions, and external APIs. Azion provides templates and guides for LangChain and LangGraph-based agent architectures.

Question 7

How do I migrate from Cloudflare Workers AI?

Accepted Answer

Migration is straightforward due to OpenAI-compatible APIs on both platforms. Update your base URL to point to Azion AI Inference endpoints, migrate any LoRA adapters, and integrate with Azion Functions. If you use Cloudflare Vectorize, migrate to Azion SQL Database Vector Search for built-in vector storage.

Question 8

How does pricing compare to other platforms?

Accepted Answer

AI Inference uses straightforward per-request pricing without abstract units like "neurons." You pay for inference requests based on model and token usage—no idle costs, no capacity commitments. This transparency makes cost forecasting predictable compared to neuron-based billing models.

Question 9

How do I deploy AI inference into my application?

Accepted Answer

Create an AI Inference endpoint, then integrate it into your request flow using Applications and Functions. This adds AI capabilities to existing APIs and user experiences with distributed execution, managed scaling, and automatic failover.

Global AI inference on managed infrastructure

Built-in reliability

OpenAI-compatible API

Pay for usage

Deploy from your local environment

Fine-tune with LoRA

From hello world to production AI workloads

What you can build with AI Inference

AI agents for automated workflows

AI-powered applications (RAG + search)

Image generation and visual AI

Speech-to-text and audio processing

Customer support copilot

Automated threat detection and takedown

Primitives that Scale with You

Frequently Asked Questions

Build once.Run everywhere.