AIVAX Documentation

AIVAX is an AI orchestration platform for building, operating, and evaluating AI applications through one account and API surface. Use hosted or bring-your-own-key (BYOK) models, then add reusable instructions, knowledge, tools, media, user channels, and background processing as your product grows.

Choose where to start #

• Make your first model call: follow Getting Started for a minimal OpenAI-compatible chat completion.
• Understand the platform: read the Overview to choose between direct inference, AI Gateways, RAG, generations, Batch, and other products.
• Prepare a production integration: review Authentication, Pricing, and Plans and limits.

Build an AI application #

• Inference — generate responses with hosted or BYOK models through an OpenAI-compatible API.
• AI Gateways — reuse a model, instructions, RAG, skills, tools, moderation, and inference settings as one assistant runtime.
• RAG collections — index your own knowledge for semantic search and grounded answers.
• Rerankers — reorder candidate documents by relevance, with or without a managed collection.
• Skills — package reusable instructions and operating knowledge for AI Gateways.
• Tools and MCP — connect assistants to AIVAX capabilities and external systems.
• Chat clients — publish a gateway through web chat or supported messaging integrations.

Process text and media #

• Text classification and text segmentation — prepare documents for routing, analysis, and retrieval.
• Image generation — create or edit images from text and reference images.
• Speech generation and audio transcription — convert between text and audio.
• Media descriptions — turn images, audio, video, or files into text for downstream processing.
• Voice Sessions — build low-latency, two-way voice experiences.

Operate at scale and improve quality #

• Batch — run the same AI workflow over many independent items in the background.
• Agentic Tests — evaluate complete, goal-oriented conversations and track repeatable gateway regressions.
• Structured responses — validate generated JSON against an application contract.
• MCP utilities — expose account, collection, documentation, web, and inference capabilities to compatible agents.

For endpoint schemas and generated request details, use the AIVAX API reference.