Kimi K2.6 API

MODEL NAME

kimi-k2.6

BASE URL

https://api.moonshot.ai/v1

WORKS WITH

The OpenAI SDK. An Anthropic-style address is also offered

CONTEXT

262,144 tokens, input and output together

DEFAULT OUTPUT LIMIT

32,768 tokens (max_tokens)

THINKING

On by default. Can be switched off

INPUT

Text and images. Video too, through Moonshot's API

PRICE PER MILLION TOKENS

$0.95 in · $0.16 cached · $4.00 out

From Moonshot's Kimi K2.6 quickstart and price page. Prices exclude tax.

1. Sign in to Moonshot's API platform at platform.kimi.ai and add a small balance. The minimum is $1.
2. Create an API key in the console. Copy it straight away.
3. Save it as an environment variable named MOONSHOT_API_KEY. Do not paste it into your code.
4. For Python, install the OpenAI SDK: pip install --upgrade "openai>=1.0". For Node, run npm install openai.

Need more detail on keys and accounts? See Kimi API setup.

All three examples ask Kimi K2.6 a simple question and print the answer.

curl https://api.moonshot.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -d '{
    "model": "kimi-k2.6",
    "max_tokens": 2048,
    "messages": [
      {"role": "user", "content": "Explain what an API is in two sentences."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MOONSHOT_API_KEY"],
    base_url="https://api.moonshot.ai/v1",
)

response = client.chat.completions.create(
    model="kimi-k2.6",
    max_tokens=2048,
    messages=[
        {"role": "user", "content": "Explain what an API is in two sentences."}
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MOONSHOT_API_KEY,
  baseURL: "https://api.moonshot.ai/v1",
});

const response = await client.chat.completions.create({
  model: "kimi-k2.6",
  max_tokens: 2048,
  messages: [
    { role: "user", content: "Explain what an API is in two sentences." },
  ],
});

console.log(response.choices[0].message.content);

Written for this guide in the standard OpenAI format, using the address, model name and settings from Moonshot's quickstart. Notice what is missing: no temperature setting.

Thinking is switched on unless you say otherwise. With it on, the reply has two parts: reasoning_content, the thinking, and content, the answer. With it off, you get the answer straight away and pay for fewer output tokens.

curl https://api.moonshot.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -d '{
    "model": "kimi-k2.6",
    "thinking": {"type": "disabled"},
    "messages": [
      {"role": "user", "content": "Give me three names for a bakery."}
    ]
  }'

response = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[
        {"role": "user", "content": "Give me three names for a bakery."}
    ],
    extra_body={"thinking": {"type": "disabled"}},
)

print(response.choices[0].message.content)

The setting and the Python extra_body method are from Moonshot's quickstart. The advice on when to use each mode is ours. The Python snippet continues from the example in Step 2.

Moonshot fixes several settings for this model. Sending any other value returns an error, so the simplest approach is to leave them out. Note that the fixed temperature depends on the thinking mode.

On a small screen, swipe the table sideways to see every column.

Many libraries send a temperature by default. If yours does, look for a way to remove it.

Tools let the model do real work: search, read files, run code. You describe each tool, the model asks to use one, your code runs it and sends the result back.

For a full tool loop in Python, see the example on the Kimi K2.7 Code API page. The pattern is the same. Search pricing: Web Search API pricing.

On a small screen, swipe the table sideways to see every column.

Enter a month's usage to compare the two.

• Cached input is text the model has seen before. It is applied automatically when requests start with the same text, so put fixed instructions first.
• Batch is for jobs that can wait. You submit many requests together and collect the results later.
• Thinking counts as output. Switching it off for simple requests is the easiest saving.

List prices before tax, from Moonshot's price pages. More: Kimi API pricing · rate limits and enterprise pricing

On a small screen, swipe the table sideways to see every column.

From Moonshot's error code page and Kimi K2.6 quickstart. More help: Kimi not working?