How much does Kimi K2.7 Code cost through Final Router?

$0.95 per million input tokens and $4 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.

Does Kimi K2.7 Code train on my data?

On the tier we route to, Moonshot AI may use prompts for training - check which key you connected.

How do I call Kimi K2.7 Code?

Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "moonshot/kimi-k2.7-code". Your existing code does not change.

Moonshot AI · model

Kimi K2.7 Code

Agentic coding, Long context, Tool use. Called through Final Router's one OpenAI-compatible endpoint at Moonshot AI's list price, with no markup on tokens.

Model id: moonshot/kimi-k2.7-code

Input price$0.95per 1M tokens

Output price$4per 1M tokens

Context window262Ktokens

Typical speed1.1smedian

Quality score89/100composite

ProviderMoonshot AIprocessed in SG

Cached input$0.19per 1M, cache read

Cache writeIncludedautomatic, no write fee

Verified 2026-08-24Moonshot AI's own list price, with no markup on tokens - a 5.5% fee applies only when you add credits.

Call Kimi K2.7 Code in one line

Kimi K2.7 Code speaks through the same OpenAI-compatible endpoint as every other model. Point your existing client at Final Router, set the model id, and you also get automatic fallback, spend caps and usage tracking - none of which the provider gives you directly.

Call Kimi K2.7 Code

from openai import OpenAI

client = OpenAI(
    api_key="fr_live_...",                     # your Final Router key
    base_url="https://finalrouter.com/api/v1"  # the only line you change
)

resp = client.chat.completions.create(
    model="moonshot/kimi-k2.7-code",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Data & residency

The international API (api.moonshot.ai) is run by their Singapore entity, which states data is stored on servers in Singapore. The parent company is Beijing-based; the .cn API is a separate service we do not call.

Training: may use prompts for training on the tier we route to. Retention: Input and generated content is used to optimise their models; kept as long as needed for the purposes in their policy, with no fixed period published.

Moonshot AI's policy, read 2026-08-24 →

Route it, don't pin it

Name Kimi K2.7 Code as your first choice and let a policy fall back to another model when the provider is down - your request still gets answered, and the log shows exactly what happened.

Start free

Kimi K2.7 Code FAQ

How much does Kimi K2.7 Code cost through Final Router?: $0.95 per million input tokens and $4 per million output tokens - the provider's own list price, with no markup on tokens. A 5.5% fee applies only when you add credits.
What is Kimi K2.7 Code's context window?: 262,144 tokens.
Does Kimi K2.7 Code train on my data?: On the tier we route to, Moonshot AI may use prompts for training - check which key you connected.
How do I call Kimi K2.7 Code?: Point any OpenAI-compatible client at https://finalrouter.com/api/v1 with your Final Router key and set model to "moonshot/kimi-k2.7-code". Your existing code does not change.

Compare with

All comparisons

Kimi K2.7 Code vs Muse Spark 1.2 Kimi K2.7 Code vs Grok Build 0.1 Kimi K2.7 Code vs DeepSeek V4 Pro Kimi K2.7 Code vs Grok 4.3

Muse Spark 1.2Meta

$1.25 in$4.25 out1.048576M ctx

Agentic coding · Huge context · Tool use

Grok Build 0.1xAI

$1 in$2 out256K ctx

Agentic coding · Cheap · Tool use

DeepSeek V4 ProDeepSeek

$0.66 in$1.98 out1M ctx

Reasoning · Huge context · Very cheap

Grok 4.3xAI

$1.25 in$2.5 out1M ctx

Huge context · Cheap · Reasoning

kimi-k2-7-codeLatency and quality are seed figures used for routing order, not billing. Prices are what you are charged.