opendunes

Kimi K2 Thinking

by Moonshot AIReleased 6 November 2025

Kimi K2 Thinking reads text and writes text back, thinking step by step before it answers and using the tools you connect to it between steps. It keeps 256 pages in mind and stays on course through 200 to 300 tool uses in a row, which fits research, coding and writing jobs that run on their own for hundreds of steps.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,62 DA per message3 000 DA buys about 4 800 messages

One message, the ordinary use

1 000 tokens sent× 199,70 DA per 1M0,20 DA
500 tokens back× 832,09 DA per 1M0,42 DA
Total≈ 0,62 DA

Every rate

Meter↑ you send↓ comes back
Text tokens199,70 DA832,09 DA
Cached tokens read49,93 DA

per 1M tokens

Answer a quick question≈ 0,24 DA
Reply to a customer email≈ 0,45 DA
Translate a full page of text≈ 0,81 DA
Write a one-page draft≈ 0,81 DA
Review a pull request of about 400 lines≈ 2,20 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Novita…
↑ Sent, per 1M
199,70 DA
↓ Back, per 1M
832,09 DA
Cache read
49,93 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Novita199,70 DA832,09 DA49,93 DA………

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
moonshotai/kimi-k2-thinking
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="moonshotai/kimi-k2-thinking",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kstopseedfrequency_penaltypresence_penaltyrepetition_penalty

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Questions about Kimi K2 Thinking

  • How much does Kimi K2 Thinking cost in dinars?

    About 0,62 DA per message. ↑ 199,70 DA · ↓ 832,09 DA per 1M tokens.

  • Is Kimi K2 Thinking free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is Kimi K2 Thinking best for?

    Kimi K2 Thinking reads text and writes text back, thinking step by step before it answers and using the tools you connect to it between steps. It keeps 256 pages in mind and stays on course through 200 to 300 tool uses in a row, which fits research, coding and writing jobs that run on their own for hundreds of steps.

  • Kimi K2 Thinking or Kimi K2 0905?

    Kimi K2 0905 costs the same for the same message.

  • How do I pay for Kimi K2 Thinking without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Kimi K2 Thinking included, is paid from that balance. No foreign card, no conversion.

  • Does Kimi K2 Thinking work in Arabic, French or Darja?

    Moonshot AI names no languages for Kimi K2 Thinking. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 262K tokens in one request, about 260 pages. It writes up to 74 000 words at once.

  • Is Kimi K2 Thinking open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes Kimi K2 Thinking, and when was it released?

    Moonshot AI. Released 6 November 2025.

Other Moonshot AI models, priced in dinars

See all Moonshot AI models
Kimi K3.1 ProMoonshot AI · Oct 23, 2026

#1 for interface design · This model accepts text, pictures, and video, allowing it to read up to 1000 pages of information at once. It is designed to handle complex, long-running coding and reasoning tasks. A key feature is its ability to process visual and auditory data alongside written text. However, it is limited to generating text responses and cannot search the internet.

Thinks firstUses your tools1 000 pages at once
≈2,33 DAper message
View model
Kimi K3Moonshot AI · Jul 16, 2026

#3 for websites · Kimi K3 reads text, pictures and video and writes text back, taking in about a thousand pages at once. You can download it and run it yourself, and it thinks before it answers. It is built for work inside large code projects: it uses connected tools, finds bugs, and revises its code from screenshots, log files, test results and what happens when the program runs.

#18 of 119 for codingThinks firstUses your tools
≈2,73 DAper message
View model
Kimi K2.6Moonshot AI · Apr 20, 2026

#2 for slide decks · Kimi K2.6 reads text and pictures and writes text back, keeping about 256 pages in mind, and it thinks before it answers unless you switch that off for quicker replies. It is aimed at long coding runs across Go, Rust and Python projects and at turning a written description or a mock-up into a working screen, and it can split a job across hundreds of helper copies of itself working side by side.

Thinks firstUses your tools260 pages at once
≈0,78 DAper message
View model
Kimi K2.7 CodeMoonshot AI · Jun 12, 2026

The coding-focused Kimi K2, which always thinks and keeps its full reasoning from turn to turn, reading text and images over 256K for end-to-end programming and breaking agent tasks into steps

Thinks firstUses your tools260 pages at once
≈0,78 DAper message
View model