Does Kimi K2 0905 support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Kimi K2 0905 is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Kimi K2 0905 hosted?

Kimi K2 0905 runs on US hosting routes through the Opper gateway.

Is Kimi K2 0905 trained on prompts and outputs?

No. Every hosting route for Kimi K2 0905 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Kimi K2 0905?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Kimi K2 0905. Contact hello@opper.ai to receive it.

Kimi K2 0905

by Moonshot

Kimi K2 0905 is Moonshot's September 5, 2025 update of the Kimi K2 flagship. It keeps the 1 trillion total parameter Mixture-of-Experts architecture with 32 billion active parameters and extends the context window from 128K to 256K tokens for longer-horizon reasoning and code tasks. The update improves performance on software engineering benchmarks and refines front-end development, producing more useful code outputs. It strengthens tool calling for autonomous agents and handles longer documents and conversations without running out of context. Key strengths include agentic coding, multilingual support, and native tool use designed for agent-driven workflows. It supports structured output, making it suited to applications that need formatted, deterministic responses.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.60 /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 0905 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
Novita	US	Enterprise	No	$0.60	$2.50

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

Data handling per route

Each route hosting Kimi K2 0905 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Novita — 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

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#155 of 531 LLMs

TierEfficient

Output speed24 tok/s

First token1.50s

Intelligence Index23.5

Coding Index25.9

Math Index57.3

Reasoning & knowledge

MMLU-Pro

82%

GPQA Diamond

77%

Humanity's Last Exam

Long-context reasoning

52%

Coding

LiveCodeBench

61%

SciCode

31%

Agentic & tool use

Terminal-Bench Hard

23%

τ²-Bench Telecom

73%

Math & instruction following

AIME 2025

57%

IFBench

42%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Kimi K2 0905 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: "novita/kimi-k2-0905",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);