Does Kimi K2.5 Fast support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Kimi K2.5 Fast is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Kimi K2.5 Fast hosted?

Kimi K2.5 Fast runs on US hosting routes through the Opper gateway.

Is Kimi K2.5 Fast trained on prompts and outputs?

No. Every hosting route for Kimi K2.5 Fast is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Kimi K2.5 Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Kimi K2.5 Fast. Contact hello@opper.ai to receive it.

Kimi K2.5 Fast

by Moonshot

Kimi K2.5 Fast is a speed-oriented variant of the full K2.5 model, built to deliver quicker responses while keeping its native multimodal and agentic capabilities. It is based on the same 1 trillion parameter MoE architecture with 32 billion active parameters and retains the vision-language integration and reasoning of the base model. The variant supports text and image inputs alongside the agent swarm coordination paradigm, letting developers balance response speed against reasoning depth. It supports a 256K token context window and tool calling for autonomous agent workflows. It suits applications that need responsive visual reasoning, coding assistance, and tool-augmented tasks. Like the rest of the K2.5 line it uses native INT4 quantization from quantization-aware training, which keeps quality close to full precision while lowering memory use.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.50 /1M

Output price

$2.50 /1M

US residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

Kimi K2.5 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
Nebius	US	Enterprise	No	$0.50	$2.50

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Kimi K2.5 Fast has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Nebius — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Kimi K2.5 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 your coding agent — Claude Code, Cursor, Codex, and more — 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: "nebius/kimi-k2.5-fast",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);