262K context · — params · Modified MIT
moonshot/kimi-k2-7-code
Kimi K2.7 Code is Moonshot AI's coding-agent specialist, released 2026-06-12. A 1-trillion-parameter Mixture-of-Experts model (32B active, 384 experts) with a 256K-token context window, it targets long-horizon agentic software engineering and uses roughly 30% fewer reasoning tokens than K2.6 while scoring higher on Moonshot's coding benchmarks. Open weights under a Modified MIT license.
Reachability & verification
Live reachability
Target (Moonshot AI): https://api.moonshot.cn/v1
Live reachability probe
Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.
Pricing across providers
1Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.
| Provider | Input /1M | Output /1M | Blended | Ctx | p50 latency | API | Verified |
|---|---|---|---|---|---|---|---|
| Moonshot AIkimi-k2.7-code | ¥0.95 | ¥4 | ¥1.7125 | 262K | — | OAI | 84d ago |
Works with
Any OpenAI-compatible client works — point the base URL at the provider endpoint.
Capabilities
Code samples
from openai import OpenAI
client = OpenAI(
base_url="https://api.moonshot.cn/v1",
api_key="YOUR_API_KEY",
)
resp = client.chat.completions.create(
model="kimi-k2.7-code",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)curl https://api.moonshot.cn/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.7-code",
"messages": [{"role": "user", "content": "Hello!"}]
}'import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.moonshot.cn/v1",
apiKey: "YOUR_API_KEY",
});
const resp = await client.chat.completions.create({
model: "kimi-k2.7-code",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Technical specs
Context
262K
Max output
262K
Parameters
—
Release
—
Training cutoff
—
License
Modified MIT
Similar models
Frequently asked questions
How much does Kimi K2.7 Code cost?
The cheapest tracked blended price is ¥1.7125 per 1M tokens on Moonshot AI. See the pricing matrix above for input/output splits per provider.
Can I use Kimi K2.7 Code from outside China?
Availability depends on the hosting provider. Use our Path Planner on the Moonshot AI page to map a verified official-vs-brokered access path, including payment and KYC constraints.
Is Kimi K2.7 Code open source?
Yes — Kimi K2.7 Code is open-weight under the Modified MIT license. You can self-host it or use any listed inference provider.
Is Kimi K2.7 Code OpenAI-compatible?
Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.
What is the maximum context window?
Kimi K2.7 Code supports up to 262K tokens of context with a maximum output of 262K tokens.
Need verified access to Kimi K2.7 Code?
We broker vetted intros to Moonshot AI — payment, KYC and endpoint verification handled.