opendunes

Inkling 2 Small

New

by ThinkingmachinesReleased 9 November 2026

This model reads text and pictures together — about a thousand pages in one go — and writes answers of up to 940 pages. It suits work where you hand it a long pile of documents, reports or scans and want a thought-through answer back, since it works out its reasoning before speaking. It also runs the same question over and over more cheaply than a first pass, which helps for repeated daily jobs. It cannot look things up on the web, so questions needing fresh information belong with a model that can search.

TakesTextImages
GivesText

Where your request runs

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

PrimeIntellect…
↑ Sent, per 1M
49,93 DA
↓ Back, per 1M
166,42 DA
Cache read
9,99 DA
Latency
…
Throughput
…
DeepInfra5 % off…
↑ Sent, per 1M
Was 99,8594,86 DA
↓ Back, per 1M
Was 332,83316,19 DA
Cache read
Was 9,999,49 DA
Latency
…
Throughput
…
Modal…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
332,84 DA
Cache read
9,99 DA
Latency
…
Throughput
…
Nebius…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
332,84 DA
Cache read
19,97 DA
Latency
…
Throughput
…
Together…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
332,84 DA
Cache read
9,99 DA
Latency
…
Throughput
…
Cloudflare…
↑ Sent, per 1M
99,85 DA
↓ Back, per 1M
332,84 DA
Cache read
9,99 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
PrimeIntellect49,93 DA166,42 DA9,99 DA………
DeepInfra5 % offWas 99,8594,86 DAWas 332,83316,19 DAWas 9,999,49 DA………
Modal99,85 DA332,84 DA9,99 DA………
Nebius99,85 DA332,84 DA19,97 DA………
Together99,85 DA332,84 DA9,99 DA………
Cloudflare99,85 DA332,84 DA9,99 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.

≈ 0,27 DA per message3 000 DA buys about 11 000 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 99,85 per 1M× 99,85 DA per 1M0,10 DA
500 back500 tokens back× 332,84 per 1M× 332,84 DA per 1M0,17 DA
Total≈ 0,27 DA

Every rate

Meter↑ you send↓ comes back
Text tokens99,85 DA332,84 DA
Cached tokens read9,99 DA

per 1M tokens

Everyday jobs, priced

Read a four-page brief with charts and get a one-page decision summary back≈ 1,73 DA
Check a six-page contract for risky wording and get plain notes on each clause≈ 2,60 DA
Run the same customer question fifty times and keep the answers≈ 103,18 DA
Have an 800-page archive summarised into a long written report≈ 346,15 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

See it in action

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

Understands images
You send

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photoTry in Chat Lab
Structured output
You send

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

customer-email.txtTry 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
thinkingmachines/inkling-2-small
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-2-small",
    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_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

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
9 Nov 2026
Full API reference

Questions about Inkling 2 Small

How much does Inkling 2 Small cost in dinars?

About 0,27 DA per message. ↑ 99,85 DA · ↓ 332,84 DA per 1M tokens.

Is Inkling 2 Small 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 Inkling 2 Small best for?

This model reads text and pictures together — about a thousand pages in one go — and writes answers of up to 940 pages. It suits work where you hand it a long pile of documents, reports or scans and want a thought-through answer back, since it works out its reasoning before speaking. It also runs the same question over and over more cheaply than a first pass, which helps for repeated daily jobs. It cannot look things up on the web, so questions needing fresh information belong with a model that can search.

How do I pay for Inkling 2 Small without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Inkling 2 Small included, is paid from that balance. No foreign card, no conversion.

Does Inkling 2 Small work in Arabic, French or Darja?

Thinkingmachines names no languages for Inkling 2 Small. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

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

Is Inkling 2 Small open source?

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

Who makes Inkling 2 Small, and when was it released?

Thinkingmachines. Released 9 November 2026.

Other Thinkingmachines models, priced in dinars

See all Thinkingmachines models
InklingThinkingmachines · Jul 17, 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.

Thinks firstUses your tools520 pages at once
≈1,01 DAper message
View model
Inkling SmallThinkingmachines · Jul 30, 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.

Thinks firstUses your tools520 pages at once
≈0,35 DAper message
View model
Inkling Small (batch)Thinkingmachines · Jul 30, 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.

Thinks firstUses your tools520 pages at once
≈0,28 DAper message
View model