by ThinkingmachinesReleased 17 July 2026
Inkling reads text, pictures and audio and writes text back, keeping about 520 pages in mind at once. Its maker lets you download it and run it yourself. It is built for thinking problems through, coding, working with the tools you connect to it, answering from your own documents and conversations in many languages. Inkling Small is the smaller, more efficient member of the family when that is enough.
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 | 332,84 DA | 1 347,98 DA |
| Cached tokens read | 56,58 DA |
per 1M tokens
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Together | 332,84 DA | 1 347,98 DA | 56,58 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.
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 LabTwo lines to welcome a shop in Oran.
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 LabTry 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="thinkingmachines/inkling",
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_pstopfrequency_penaltypresence_penaltyrepetition_penaltylogit_biasReasoning
Let it think before answering — and see the thinking.
reasoningreasoning_effortinclude_reasoningTools
Let the model call your functions.
toolstool_choiceAbout 1,01 DA per message. ↑ 332,84 DA · ↓ 1 347,98 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Inkling reads text, pictures and audio and writes text back, keeping about 520 pages in mind at once. Its maker lets you download it and run it yourself. It is built for thinking problems through, coding, working with the tools you connect to it, answering from your own documents and conversations in many languages. Inkling Small is the smaller, more efficient member of the family when that is enough.
Deposit dinars with your Edahabia or CIB card. Every model, Inkling included, is paid from that balance. No foreign card, no conversion.
Thinking Machines names English, with general multilingual ability in other languages. Arabic, French and Darja are not named.
It reads text, images and audio. Up to 524K tokens in one request, about 520 pages. It writes up to 354 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
Thinkingmachines. Released 17 July 2026.
Inkling Small reads text, pictures and audio and writes text back, keeping about 520 pages in mind at once, and you can download it and run it yourself. It is the smaller and leaner sibling of Inkling, suited to thinking problems through, coding, working with the tools you connect to it, and conversations in many languages.
Inkling Small reads text, pictures and audio and writes text back, keeping about 520 pages in mind at once, and you can download it and run it yourself. It is the smaller and leaner sibling of Inkling, suited to thinking problems through, coding, working with the tools you connect to it, and conversations in many languages.
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 No.
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.
Run an agent that plans and calls your tools
Uses your tools · Thinks first
Refactor a module across a large codebase
Answer questions about a recorded interview
Audio