Inference API

Point your OpenAI client at the EU.

The Akumi Inference API is OpenAI-compatible and served on EU infrastructure. Change one base_url and your existing code runs on EU-resident models: chat, tools, streaming, and structured output, metered per use and audited from the first token.

Start free Read the API docs

POST https://api.akumi.cloud/v1/chat/completions

quickstart.py

              from openai import OpenAI
               
              client = OpenAI(
                  # the only line that changes
                  base_url="https://api.akumi.cloud/v1",
                  api_key=os.environ["AKUMI_API_KEY"],
              )
               
              client.chat.completions.create(
                  model="mistral/mistral-small-2603",
                  messages=[
                      {"role": "user", "content": "Summarize this contract."},
                  ],
                  stream=True,
              )
            

Change one line. Keep your whole stack.

No new SDK, no rewrite, no migration project. Keep the OpenAI client you already build with, point it at Akumi, and add your key. Chat, function calling, streaming, and JSON mode behave exactly as they do today, now on EU-resident models with one metered bill.

.env

- OPENAI_BASE_URL=https://api.openai.com/v1

+ OPENAI_BASE_URL=https://api.akumi.cloud/v1

Your stack runs unchanged.

The endpoints, request bodies, and responses match the OpenAI API, so the libraries, frameworks, and tools you already use just work.

Chat Completions

POST /v1/chat/completions with the full message and parameter surface you already send.

Streaming

Token-by-token server-sent events, the same response you get from stream=true.

Tools & function calling

Define tools, let the model call them, and steer with tool_choice. Tool content is governed too.

Structured output

response_format with a JSON schema for reliable, typed responses your code can trust.

Embeddings

POST /v1/embeddings on EU-hosted models for search, clustering, and retrieval.

Native /v1/process

A native endpoint when you want the full Akumi pipeline response, residency and modules included.

Sovereign by default, governed on every call.

EU-resident inference

Requests are served on EU infrastructure. Inference and storage stay in the EU, with no US CLOUD Act exposure.

Egress guard

Routing to a non-EU model is blocked unless you explicitly allow it, with personal data pseudonymized before it ever leaves.

Audited from the first token

Every request is metered and written to a metadata-only audit trail with its model, region, and modules. Hand compliance the log.

Many models, one endpoint.

The model router puts every model behind the same base_url. Pick an EU-sovereign model, or allow an external one under policy. Set routing rules, automatic fallback, and bring your own provider keys.

Policy-based routing Decide per data class which models are allowed, with crown-jewel data kept EU-only.
Automatic fallback A provider hiccup fails over to the next allowed model, so a request rarely just errors.
Bring your own keys Use your own provider credentials when you want, billed and audited through one place.

GET /v1/models api.akumi.cloud

mistral/mistral-small-2603 EU-resident

mistral/mistral-large-2512 EU-resident

akumi/embed-eu EU-resident

openai/gpt-5.4 external · governed

anthropic/claude-sonnet external · governed

Pay for tokens, not seats.

Base inference is metered per token and request. Every governance module you switch on is metered on its own line, so the bill reads like the work the platform actually did. No seats, no minimums, no surprise tiers.

Per token and request

Base inference is metered on real usage and drawn from prepaid credits.

Per module

PII firewall, RAG, memory, guard, and cache each meter independently when used.

One transparent bill

A single ledger of credits with per-line detail, exportable for finance and compliance.

Start with one `base_url`.

Create a key, point your client at Akumi, and ship on EU-sovereign models today.