Kimi K2.6

✓ Official API· served by

DigitalOcean

Kimi K2.6 is a Moonshot AI model for coding and agentic tasks, with a 256K-token context and tool calling. It thinks when you ask for reasoning and answers directly otherwise.

The real Moonshot model

Same weights, same API, same answers. We change only how you pay for it: one key for every maker, one bill, no separate account to open. Every figure on this page comes from Moonshot’s own page — check it.

Maker's own page

Price

input / output · per 1M tokens

DigitalOcean

Official price

$0.95 / $4.00

Context

262,144

up to 262,144 out

262,144 by default here

Modalities

ToolsReasoning

What it would cost you

Requests

Input tokens per request

Output tokens per request

1000 tokens is roughly 750 English words.

Estimated total$3.90

How it is served

Standard

Requests are retried automatically if a provider is unavailable.

Similar models

Models built for the same kind of work, at a similar price.

DeepSeek V4 Pro 0813

DeepSeek

-30% today

1000k context

$1.27$0.89

Out

$3.82$2.67

per 1M tokens

Gemini 2.5 Pro

Google

-30%

1049k context

$1.25$0.88

Out

$10.00$7.00

per 1M tokens

GLM-5.3

Z.ai

-30% today

1049k context

$1.13$0.79

Out

$3.96$2.77

per 1M tokens

We do not mark up the price of tokens. It is the same price the maker charges.

Use it from your code

Model:moonshotai/kimi-k2.6

main.py

OpenAI Specification v1.0

from openai import OpenAI

# Works with the official openai package (pip install openai)
client = OpenAI(
    base_url="https://api.flintbeam.com/v1",
    api_key="sk-live-your-api-key"
)

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=[
        {"role": "system", "content": "You are an experienced software engineer."},
        {"role": "user", "content": "Describe the architecture of a distributed cache."}
    ],
    temperature=0.7,
    max_tokens=1500
)

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