by Moonshot AIReleased 23 October 2026
#1 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.
You pay for what each request uses. No subscription, no minimum.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 665,67 DA | 3 328,36 DA |
| Cached tokens read | 66,57 DA |
per 1M tokens
17 companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Relace | 109,40 DA | 2 700,96 DA | 66,57 DA | … | … | … |
| Sail ResearchUnited States | 115,16 DA | 5 518,75 DA | 57,58 DA | … | … | … |
| Sail Research | 115,16 DA | 5 518,75 DA | 57,58 DA | … | … | … |
| AkashML | 582,46 DA | 3 328,36 DA | 59,91 DA | … | … | … |
| PrimaLabs | 599,10 DA | 2 995,52 DA | 59,91 DA | … | … | … |
| Wafer | 599,10 DA | 2 995,52 DA | 59,91 DA | … | … | … |
| InferenceNet | 599,10 DA | 2 995,52 DA | 59,91 DA | … | … | … |
| InferenceNetUnited States | 599,10 DA | 2 995,52 DA | 59,91 DA | … | … | … |
| DeepInfra5 % offUnited States | … | … | … | |||
| MorphUnited States | 635,05 DA | 3 994,03 DA | 156,43 DA | … | … | … |
| Fireworks | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| WaferUnited States | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| PhalaUnited States | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| DigitalOcean | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Parasail | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Modal | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Phala | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Nebius | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Together | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| Moonshot AIAsia | 665,67 DA | 3 328,36 DA | 66,57 DA | … | … | … |
| AlibabaAsia | 765,52 DA | 3 827,61 DA | 76,55 DA | … | … | … |
You pay the price of the provider that served your request. Prices read 15:06 · speed over the last 30 minutes · uptime over 3 days.
Real requests, real replies. Try any of them yourself — one click, pre-filled.
What's the total on this invoice, and when is it due?
invoice-scan.jpg · photoThe total is 42 300,00 DA, due 5 September 2026. Worth a double-check: the handwritten day could read as 8 instead of 3.
Try in Chat LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry your own request — same model, pre-selected.
Open Chat LabSwap the base URL and the key. Your OpenAI code runs unchanged.
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",
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.
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_biaslogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoningreasoning_effortinclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceAbout 2,33 DA per message. ↑ 665,67 DA · ↓ 3 328,36 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
#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.
Deposit dinars with your Edahabia or CIB card. Every model, Kimi K3.1 Pro included, is paid from that balance. No foreign card, no conversion.
Moonshot AI names no languages for Kimi K3.1 Pro. Arabic, French and Darja: not stated.
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.
Yes, its weights are public. Open weights on Hugging Face
Moonshot AI. Released 23 October 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.
#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.
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
Kimi K2.5 reads text and pictures and writes text back, and it keeps about 256 pages in mind at once. It is built to turn a picture, such as a mock-up of a screen, into working code, and to use the tools you connect to it on its own; Moonshot trained it on pictures and text together, on top of Kimi K2. Kimi K2.6 is the later release for longer coding runs and screen building.
From what its maker and two benchmark sites publish, and where it stands on OpenDunes. Read 7 Nov 2026.
Thinks first
Works through the problem before it answers.
Uses your tools
Can call functions your code provides.
Fills your JSON
Answers in the JSON shape you give it.
Searches the web No.
Can look things up online while it answers.
Cheaper on repeats
A prompt it saw a moment ago costs less the second time.
Open weights
The model's weights are public.
Structure complex data into a defined format
Fills your JSON · Thinks first
Solve multi-step problems using external resources
Uses your tools · Thinks first
Process large batches of similar data efficiently
Cheaper on repeats · Fills your JSON