Routes and contracts

One API. Full provider control.

Integrate leading AI models and specialized agents directly into your apps with a single, enterprise-ready API.

Feza APIs Build with enterprise AI.

Completion API

Access leading LLMs from OpenAI, Anthropic, Mistral, and Google for text generation and reasoning.

Embedding API

Generate high-quality embeddings for semantic search, similarity matching, and RAG.

Agent API

Create and manage custom AI agents programmatically.

Knowledge Folder API

Manage your knowledge base programmatically for RAG and document processing.

API List

None yet

Feza does not offer publicly accessible model APIs. The details shown are strictly informational; model names, providers, pricing, and processing regions are exclusively available to enterprise users.

Explore the API structure

FAQ

The Feza API allows developers to integrate leading AI models, agents, and knowledge management features directly into their own applications with enterprise-grade security and full control.

You can access models from OpenAI, Anthropic, Mistral, and Google, as well as in-region open-weight models, all through a single interface.

Yes. The platform provides both an Embedding API and a Knowledge Folder API to run semantic search, document retrieval, and end-to-end RAG workflows.

Yes. The Agent API allows you to programmatically create, update, and manage AI agents equipped with custom instructions, connected knowledge bases, and tools.

No. Thanks to Feza's persistent route and contract architecture, you do not need to update your code or API endpoint even if you switch the underlying model or provider.

All requests are authenticated via a secure API key sent in the authorization header. Credentials remain strictly server-side, and every request is verified against your organization's access boundaries and DLP policies before execution.