Does Kimi K2.7 Code Fast support zero data retention?

No. The routes serving Kimi K2.7 Code Fast retain content; see the per-route data-handling section for each route's logging stance and retention window.

Where is Kimi K2.7 Code Fast hosted?

See the per-route table for Kimi K2.7 Code Fast hosting locations and residency details.

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

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

Is a GDPR DPA available for Kimi K2.7 Code Fast?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Kimi K2.7 Code Fast. Contact hello@opper.ai to receive it.

Kimi K2.7 Code Fast

by Moonshot

Kimi K2.7 Code Fast delivers Moonshot AI's coding-focused Kimi K2.7 Code through a speed-optimized serving tier that sustains over 100 tokens per second. Released in June 2026 under a modified MIT license, the underlying model is a mixture-of-experts design with one trillion total parameters and 32 billion active per token, shaped around real engineering work such as reading unfamiliar repositories, planning multi-file changes, and running tools and tests. Against its K2.6 predecessor it posts clear gains on Moonshot's coding benchmarks while spending roughly 30 percent fewer thinking tokens, and the Fast tier keeps agent loops responsive without changing the model's behavior. With a 262K context window, image input, tool calling, and structured output, it fits long-horizon coding agents, CI automation, and refactoring jobs that run for many turns.

Call Kimi K2.7 Code Fast 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

$1.90 /1M$0.38 cache read

Output price

$8.00 /1M

No training by default
GDPR DPA available

Available routes

Kimi K2.7 Code Fast runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Tencent Cloud	Multi		No	$1.90	$8.00	$0.38

Data handling per route

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

Tencent Cloud — Multi-region

Content is retained: limited debug logs, 30-day retention. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention: Retained: limited debug logs, 30-day retention.
Training: No training on customer data.
Logging: Limited debug logs (30-day retention)
Abuse monitoring: On by default, holds flagged content
Caching: Content cached for replay
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Kimi K2.7 Code Fast 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 Fast 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: "tencent:sg/kimi-k2.7-code-highspeed",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);