opendunes

Kimi K3.1 Pro (batch)

New

by Moonshot AIReleased 23 October 2026

#2 for interface designThis 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.

TakesTextImagesVideo
GivesText

Where your request runs

Two companies run this model. OpenDunes sends each request to one of them. DA per 1M tokens: ↑ what you send · ↓ what comes back.

MorphUnited States…
↑ Sent, per 1M
123,81 DA
↓ Back, per 1M
1 858,22 DA
Cache read
33,28 DA
Latency
…
Throughput
…
Sail Research…
↑ Sent, per 1M
232,98 DA
↓ Back, per 1M
1 997,01 DA
Cache read
33,28 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
MorphUnited States123,81 DA1 858,22 DA33,28 DA………
Sail Research232,98 DA1 997,01 DA33,28 DA………

You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.

What it costs

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

≈ 1,05 DA per message3 000 DA buys about 2 800 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 123,81 per 1M× 123,81 DA per 1M0,12 DA
500 back500 tokens back× 1 858,22 per 1M× 1 858,22 DA per 1M0,93 DA
Total≈ 1,05 DA

Every rate

Meter↑ you send↓ comes back
Text tokens123,81 DA1 858,22 DA
Cached tokens read33,28 DA

per 1M tokens

Everyday jobs, priced

Analyzing a large document for key insights≈ 123,81 DA
Responding to a detailed query involving multiple inputs≈ 991,02 DA
Generating a comprehensive technical report≈ 1 746,73 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.
Add creditDeposits from 100 DA, withEdahabiaCIB

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-k3.1-pro:batch
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-k3.1-pro:batch",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

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

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_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
1 048 576 tokens
Max output
943 718 tokens
Reads at once
≈ 1 000 pages
Longest reply
≈ 708 000 words
Tokenizer
Other
Released
23 Oct 2026
Full API reference

Questions about Kimi K3.1 Pro (batch)

How much does Kimi K3.1 Pro (batch) cost in dinars?

About 1,05 DA per message. ↑ 123,81 DA · ↓ 1 858,22 DA per 1M tokens.

Is Kimi K3.1 Pro (batch) free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is Kimi K3.1 Pro (batch) best for?

#2 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.

How do I pay for Kimi K3.1 Pro (batch) without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Kimi K3.1 Pro (batch) included, is paid from that balance. No foreign card, no conversion.

Does Kimi K3.1 Pro (batch) work in Arabic, French or Darja?

Moonshot AI names no languages for Kimi K3.1 Pro (batch). Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text, images and video. Up to 1M tokens in one request, about 1 000 pages. It writes up to 708 000 words at once.

Is Kimi K3.1 Pro (batch) open source?

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

Who makes Kimi K3.1 Pro (batch), and when was it released?

Moonshot AI. Released 23 October 2026.

Other Moonshot AI models, priced in dinars

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

#2 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
≈1,48 DAper message
View model
Kimi K3Moonshot AI · Jul 16, 2026

#4 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 118 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

Kimi K2.7 Code reads text and pictures and writes text back. It always thinks before it answers and carries that thinking through the whole conversation, and it reads up to 256 pages, which suits long programming tasks that unfold over many messages.

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