EU data residency

Kimi models hosted in the EU

Where each Kimi model runs in the EU, what the provider keeps and what it costs, route by route.

4 of 6 models11 routes7 providers2 countries

Every EU route for Kimi

One row per model and route, with each model's best route first. Token prices are per million tokens.

ModelProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$3.00$15.00$0.45
EU multi-regionNo$3.00$15.00$0.75
SwedenNo$3.41$17.07Input price
EUNo$3.75$18.77$0.94
SwedenNo$0.47$2.58$0.13
EU multi-regionNo$1.00$4.00$0.25
SwedenNo$1.54$6.14Input price
SwedenNo$0.71$3.30$0.18
EU multi-regionNo$1.25$4.50$0.31
Norway (EEA)No$0.40$2.60Input price
EU multi-regionNo$0.50$2.80$0.13

Kimi models not in the EU yet

These Kimi models run on Opper outside the EU for now, in the region shown. This page updates within the hour when one gains an EU route.

Call Kimi only in the EU

Every route has its own model id. Call that id on any plan and the request is served on that route, in that location. The examples below call Kimi K3 on Sference in the EU.

Set it up with your agent

Copy this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper and call this route.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "sference/kimi-k3",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Lock it in with a rule

A model access rule with Inference location: EU, set for your organization or a project, means no LLM or embedding call can reach a route outside the EU, even by mistake. Rules are part of the Control Plane. How model access rules work

Who you contract with

Company
Opper Technology AB, Sweden, reg. no. 559446-3720
Certification
Processor
Opper, for every modelSub-processor list
DPA
One DPA covers the whole catalogueRead the DPA

Other model families in the EU

Frequently asked questions

Is Kimi available in the EU?

+
Yes. 4 of the 6 Kimi models on Opper run on European routes, on Sference, TensorX, Berget, GreenPT, Inceptron and 2 more in the EU multi-region, Sweden and Norway. Call the route's model id and the request is served in Europe.

Which Kimi models run in the EU?

+
Kimi K3, Kimi K2.6, Kimi K2.7 Code and Kimi K2.5. Not in the EU yet: Kimi K2 0905 and Kimi K2 Instruct.

Is Kimi GDPR (DSGVO) compliant in the EU?

+
Running Kimi on an EU route keeps processing in the EU, which settles where your data goes. The rest depends on your own processing and the service's terms. On Opper, one Data Processing Agreement covers Kimi and every other model, Opper is your single sub-processor, and each route lists what the provider keeps and whether it trains on your data. Opper is certified against ISO/IEC 27001:2022; the controls, policies and sub-processors are on https://trust.opper.ai. Read the DPA

Does Kimi cost more in the EU?

+
Sometimes. Comparing input prices, of the 4 Kimi models that also run elsewhere, 1 costs the same, 1 costs less and 2 cost more on their cheapest European route. Other hosts in Europe set their own prices, so for open-weight models the difference depends on the host. Every route's own price is in the table on this page.

How do I make sure Kimi calls never leave the EU?

+
On any plan, call an EU route's model id and the request is served there. To lock it in, set a model access rule with Inference location: EU for your organization or a project, and no LLM or embedding call to Kimi can reach a route outside the EU, even by mistake. Rules are part of the Control Plane. Model access rules

Read this list from an agent

This list as data. The same routes as JSON at opper.ai/models/eu.json (model id, provider, country, zero data retention, training and price per route) and as markdown at opper.ai/models/eu/kimi.md.

The whole catalogue. The model catalogue is public JSON at https://api.opper.ai/v3/models, no API key needed. Filter it with query parameters, for example ?type=llm&limit=3, and page through it with limit and offset. Use it when you can fetch a URL but cannot connect to an MCP server. Coding agents that use MCP can connect to https://api.opper.ai/mcp. Two of the server's tools need no account and no sign-in: list_models searches the model catalogue by name, type, provider or capability, and get_guide returns short setup guides. Everything that touches your account needs you to approve the connection in the browser first. About the MCP server

Run your AI in the EU

One API key for every EU route and one DPA for every model, with each call served where you choose.

Get startedRead the DPA