Does Kimi K3 Fast support zero data retention?

Yes. Kimi K3 Fast is available with zero data retention by default on Wafer through the Opper gateway.

Where is Kimi K3 Fast hosted?

Kimi K3 Fast runs on US hosting routes through the Opper gateway.

Is Kimi K3 Fast trained on prompts and outputs?

No. Every hosting route for Kimi K3 Fast is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Kimi K3 Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Kimi K3 Fast. Contact hello@opper.ai to receive it.

Kimi K3 Fast

by Moonshot

Moonshot Kimi K3 on Wafer's fast tier — latency-tuned US serverless inference with per-request zero data retention (Wafer-ZDR pinned by the adapter); same 2.8T-param MoE weights with the full 1M-token context window

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

Max output

Input price

$4.50 /1M

Output price

$22.50 /1M

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Kimi K3 Fast runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Wafer	US	Zero data retention	No	$4.50	$22.50

Data handling per route

Each route hosting Kimi K3 Fast has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Wafer — United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; DPA available.

Zero data retention: On by default on Pay-as-you-go.
Training: No training on customer data.
Logging: None
Third-party access: Provider may share with subprocessors / partners
GDPR DPA: DPA available
Transfer mechanism: unknown

Get started

Call Kimi K3 Fast through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "wafer/kimi-k3-fast",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);