Turn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry in Chat LabMi
Newby KtReleased 5 November 2026
This is a text-only model: you hand it writing to read and it hands writing back, taking in about 260 pages at once and writing up to 230 in reply. It is built for slow, careful work on long documents — reading a contract, a study or a report end to end, then reasoning through it and giving a well-worked-out answer. It pauses to think before replying, and it can shape its reply as a filled-in form when your program needs one. It does not look at pictures, listen to audio, search the web or run your tools, so jobs that need those are a fit for another kind of model.
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.
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.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 66,57 DA | 266,27 DA |
| Cached tokens read | 13,31 DA |
per 1M tokens
Everyday jobs, priced
- 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.
See it in action
Real requests, real replies. Try any of them yourself — one click, pre-filled.
Call it in code
Swap 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="kt/midm-k-3.0-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.
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_kfrequency_penaltypresence_penaltyrepetition_penaltylogprobstop_logprobsReasoning
Let it think before answering — and see the thinking.
reasoninginclude_reasoningStructured output
Get JSON you can parse instead of prose.
response_formatstructured_outputsTools
Let the model call your functions.
toolstool_choiceLimits
The hard numbers — what it can take in, what it can give back, and where it stops.
- Context window
- 261 795 tokens
- Max output
- 235 615 tokens
- Reads at once
- ≈ 260 pages
- Longest reply
- ≈ 177 000 words
- Tokenizer
- Other
- Released
- 5 Nov 2026
Questions about Mi
How much does Mi cost in dinars?
About 0,20 DA per message. ↑ 66,57 DA · ↓ 266,27 DA per 1M tokens.
Is Mi 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 Mi best for?
This is a text-only model: you hand it writing to read and it hands writing back, taking in about 260 pages at once and writing up to 230 in reply. It is built for slow, careful work on long documents — reading a contract, a study or a report end to end, then reasoning through it and giving a well-worked-out answer. It pauses to think before replying, and it can shape its reply as a filled-in form when your program needs one. It does not look at pictures, listen to audio, search the web or run your tools, so jobs that need those are a fit for another kind of model.
How do I pay for Mi without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, Mi included, is paid from that balance. No foreign card, no conversion.
Does Mi work in Arabic, French or Darja?
Kt names no languages for Mi. 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 177 000 words at once.
Is Mi open source?
No. Kt has not published its weights.
Who makes Mi, and when was it released?
Kt. Released 5 November 2026.
Similar models, priced in dinars
See all modelsThis model is designed to handle text, pictures, and video inputs, allowing it to read up to 130 pages of content. It specializes in generating and editing video clips, producing outputs that include both text and moving images. What sets this model apart is its native ability to process and generate video content directly. It is not suitable for tasks requiring external tool usage or the creation of structured data formats.
This is the 17 October 2026 snapshot of V4.1 Flash, the image-and-text model DeepSeek serves under its current Flash name. It keeps about a thousand pages in mind, replies up to about 393 pages, thinks first, uses your connected tools and fills in the exact form you give it. Pick it for agents and coding work that include screenshots, and when you want the newest Flash. The earlier DeepSeek V4.1 Flash is the snapshot before this one; V4 Pro 0813 is the larger model for hard reasoning.
This model accepts text, pictures, and videos as input, allowing it to read up to 130 pages of content. It specializes in creating and editing video content, converting descriptions or pictures into moving images. A key feature is its ability to search the web for information while processing complex visual data. However, it does not utilize external tools or generate structured data formats.
This model accepts text and pictures as input and produces text as output. It can process up to 1000 pages of material at one time and generate responses up to 65 pages long. It is designed for complex, real-world productivity tasks that require planning and the use of specific tools. However, it cannot access the internet to find new information.
