When was Kimi K2.7 Code released?

Moonshot released Kimi K2.7 Code on 12 Jun 2026. It is available through the Opper gateway.

Does Kimi K2.7 Code support zero data retention?

Yes. Kimi K2.7 Code is available with zero data retention on Inceptron, Lyceum, Novita, Tencent Cloud, TensorX through the Opper gateway. Other routes carry zero data retention with abuse monitoring; see each route's window in the data-handling section.

Where is Kimi K2.7 Code hosted?

Kimi K2.7 Code runs on both EU and US hosting routes through the Opper gateway. Pick the route that matches your residency requirement.

Is Kimi K2.7 Code trained on prompts and outputs?

No. Every hosting route for Kimi K2.7 Code is configured so customer prompts and outputs are not used to train models by default.

Kimi K2.7 Code

by Moonshot

Released 53 days after Kimi K2.6 · All Moonshot releases

Kimi K2.7 Code, released June 2026, is Moonshot's coding-specialized variant of the Kimi K2 line, built on the Kimi K2.6 foundation and purpose-built for software engineering rather than general chat. It uses a Mixture-of-Experts architecture with 1 trillion total parameters and 32 billion active per token, drawing on 384 experts with 8 selected plus 1 shared, and it natively handles text, image, and video input through the MoonViT vision encoder. The model is tuned for long-horizon, agentic coding, planning edits, running tools, and debugging across many steps within a 256K token context window. It shares the interleaved thinking and multi-step tool calling design of Kimi K2 Thinking while improving token efficiency, using roughly 30% fewer reasoning tokens than Kimi K2.6 on comparable work, which makes it well suited to extended coding sessions and autonomous engineering workflows. It is released as open weights under a Modified MIT License, with weights published on Hugging Face for self-hosting and fine-tuning.

Call Kimi K2.7 Code on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

262K

Max output

262K

Input price

$0.97 /1M

Output price

$4.05 /1M

Released

12 Jun 2026

Web search

Via Opper

EU residency available on Inceptron, Lyceum and TensorX
US residency available on Novita
Zero data retention on pay-as-you-go
No training by default

Available routes

Kimi K2.7 Code runs on 6 different routes through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below. In the EU it is served by Inceptron, Lyceum and TensorX. See every Kimi model hosted in the EU.

Provider	Region	Training	Input	Output	Cache read
Alibaba Cloud	Multi	No	$0.97	$4.05	Input price
Inceptron	EU	No	$0.67	$3.35	$0.16
Lyceum	EU	No	$1.25	$4.50	$0.31
Novita	US	No	$0.95	$4.00	$0.19
Tencent Cloud	Multi	No	$0.95	$4.00	$0.19
TensorX	EU	No	$1.25	$4.50	$0.31

Live routes and prices as JSON: api.opper.ai/v3/models?q=kimi-k2.7-code

Uptime and availability

Kimi K2.7 Code runs on 2 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days

Averaged across these routes on their own, a single provider reached 100% over the same window.

Daily status through the gateway, which serves each request from whichever route is healthy.

2 monitored providers serve Kimi K2.7 Code.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 4 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Kimi K2.7 Code has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Alibaba Cloud — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. GLOBAL; SCCs.

Zero data retention: With abuse monitoring, window not stated.
Training: No training on customer data.
Logging: Abuse monitoring
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
Transfer mechanism: SCCs

Inceptron — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Transfer mechanism: Not applicable — data stays in EU

Lyceum — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Subprocessor access: Subprocessors may read content
Transfer mechanism: Not applicable — data stays in EU

Novita — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Transfer mechanism: SCCs

Tencent Cloud — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: On by default, keeps nothing
Caching: Content cached for replay
Transfer mechanism: SCCs

TensorX — EU🇪🇺

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
Caching: Content cached for replay
Transfer mechanism: Not applicable — data stays in EU

Best for

Where Kimi K2.7 Code ranks among the models on Opper with a score for each use case.

Agents12.8

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#116 of 511 LLMs

TierEfficient

Output speed64 tok/s

Intelligence Index (previous version)25.8

Coding

Terminal-Bench 4.0

SciCode

48%

Agentic & knowledge work

AutomationBench

25%

GDPval

27%

GDP.pdf

11%

Briefcase (Elo)858

Terminal-Bench Hard

45%

τ²-Bench Telecom

90%

Science & reasoning

HLE Diamond

15%

Humanity's Last Exam

35%

GPQA Diamond

90%

Long-context reasoning

79%

Math & instruction following

IFBench

63%

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

Get started

Call Kimi K2.7 Code through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Kimi K2.7 Code is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

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: "kimi-k2.7-code",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);