Skip to main content
Akumi is an EU-sovereign, OpenAI-compatible inference platform. Send chat and embedding requests to a single base URL, layer governed services like the firewall, Memory and Cache onto any request, and get every call metered and audited. These docs cover the API and each service.

​
Your first request

The API is OpenAI-compatible, so point any client at the base URL with your key. Add a payment method and create one under API keys, then send a chat completion.
Prefer typed access? Reach for a client SDK for PHP, TypeScript or Python. For every endpoint, see the API reference.

​
Explore the platform

​
Inference

Model router

Route across EU and external providers with aliases and fallback.

Embeddings

Generate embeddings with EU or external models through one endpoint.

​
Governance

Firewall

Pseudonymize personal data before it reaches a model, and refuse prompts that carry hidden instructions.

Compliance reports

A signed record of residency, transfers and how data was handled.

​
Knowledge

Memory

Answer from your own documents and long-term facts, tenant-scoped.

MCP server

Connect Claude and other MCP clients to your governed knowledge.

​
Operations

Observability

Trace latency, cost and pipeline stages per request.

Cache

Reuse stored responses to cut cost and latency.

Audit log

Review a metadata-only trail of platform activity.

Usage limits

Cap what a workspace can spend per month or per day.