Model

Kimi K3 (2.8T parameters, 1M context)

Fast access (US)

Call Kimi K3 (2.8T parameters, 1M context) through an OpenAI-compatible API hosted in Europe: licence, real per-token price, hosting jurisdiction.

€3.654

Inputper 1M tokens

€18.242

Outputper 1M tokens

€0.378

Cached inputper 1M tokens

Specifications

API model id
kimi-k3
Availability
Live
Hosting jurisdiction
Fast access (US)
Served via
modal
Publisher
Moonshot AI
Parameters
2.8T
Context window
1M

Reasoning model. First call after a quiet period can take a few minutes to warm up — then it responds in seconds.

What its label means

This model is served through infrastructure controlled by a US company, which remains subject to the US CLOUD Act even when it runs in an EU region. We label it “fast access”, never sovereign, and it is flagged in the API response before you call it — so the choice is yours, made with full information.

How we draw the line: GDPR vs. the CLOUD Act →

Calling it

The API is OpenAI-compatible. Change base_url and the key, then use this model id:

client = OpenAI(
    base_url="https://getfrontiereai.eu/api/v1",
    api_key=os.environ["FRONTIERE_KEY"],
)

reply = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Bonjour"}],
)

One key covers the whole catalog — you switch models by changing a single string.

API reference

Pricing

The price you see is the price debited from your prepaid balance, margin included — not an infrastructure cost. No subscription: top up from €20, calls stop at zero.

FAQ

Is Kimi K3 (2.8T parameters, 1M context) GDPR-compliant on Frontière?

This model is labeled “fast access”, not sovereign: it is served through modal, controlled by a US company and therefore subject to the CLOUD Act even in an EU region. For regulated workloads, pick a model from the sovereign tier. In either case, Frontière stores neither the prompts nor the completions from API calls.

How much does Kimi K3 (2.8T parameters, 1M context) cost?

€3.654 per million input tokens and €18.242 per million output tokens — margin included, that is the amount debited from your prepaid balance. No subscription: you top up from €20 and calls stop when the balance reaches zero.

How do I call Kimi K3 (2.8T parameters, 1M context) from my code?

The API is OpenAI-compatible: point base_url at https://getfrontiereai.eu/api/v1, swap the key, and pass “kimi-k3” as the model field. Your SDK, scripts and tools keep working, streaming included.

Is there any behaviour I should know about?

Reasoning model. First call after a quiet period can take a few minutes to warm up — then it responds in seconds.

Other models in the catalog

See the full catalog →

Call it in minutes

Create an account, top up €20, change two lines.