opendunes

Gemini 4 Carbon

New

by GoogleReleased 10 November 2026

#1 for SVG drawingsGemini 4 Carbon takes in text, pictures, sound, video and documents, keeps about 1,000 pages in mind at once, and can write an answer up to 940 pages long. It thinks a question through before answering, so it suits long jobs such as working through a whole codebase, planning a task in many steps, or drafting a lengthy report from mixed source material. Another model in the same family handles the same inputs, but this one can hold a very long written answer in a single piece. It gives back text only, so jobs that need a picture, a sound or a clip in return call for a different kind of model.

TakesTextImagesVideoAudioFiles
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.

Google AI Studio · Flex50 % off…
↑ Sent, per 1M
Was 665,68332,84 DA
↓ Back, per 1M
Was 3 328,361 664,18 DA
Cache read
Was 33,2816,64 DA
Latency
…
Throughput
…
Google50 % off…
↑ Sent, per 1M
Was 1 331,34665,67 DA
↓ Back, per 1M
Was 6 656,723 328,36 DA
Cache read
Was 66,5633,28 DA
Latency
…
Throughput
…
Google AI Studio50 % off…
↑ Sent, per 1M
Was 1 331,34665,67 DA
↓ Back, per 1M
Was 6 656,723 328,36 DA
Cache read
Was 66,5633,28 DA
Latency
…
Throughput
…
Google50 % offEurope…
↑ Sent, per 1M
Was 1 464,48732,24 DA
↓ Back, per 1M
Was 7 322,383 661,19 DA
Cache read
Was 73,2236,61 DA
Latency
…
Throughput
…
Google50 % offUnited States…
↑ Sent, per 1M
Was 1 464,48732,24 DA
↓ Back, per 1M
Was 7 322,383 661,19 DA
Cache read
Was 73,2236,61 DA
Latency
…
Throughput
…
Google · Priority50 % off…
↑ Sent, per 1M
Was 2 396,421 198,21 DA
↓ Back, per 1M
Was 11 982,085 991,04 DA
Cache read
Was 119,8259,91 DA
Latency
…
Throughput
…
Google AI Studio · Priority50 % off…
↑ Sent, per 1M
Was 2 396,421 198,21 DA
↓ Back, per 1M
Was 11 982,085 991,04 DA
Cache read
Was 119,8259,91 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Google AI Studio · Flex50 % offWas 665,68332,84 DAWas 3 328,361 664,18 DAWas 33,2816,64 DA………
Google50 % offWas 1 331,34665,67 DAWas 6 656,723 328,36 DAWas 66,5633,28 DA………
Google AI Studio50 % offWas 1 331,34665,67 DAWas 6 656,723 328,36 DAWas 66,5633,28 DA………
Google50 % offEuropeWas 1 464,48732,24 DAWas 7 322,383 661,19 DAWas 73,2236,61 DA………
Google50 % offUnited StatesWas 1 464,48732,24 DAWas 7 322,383 661,19 DAWas 73,2236,61 DA………
Google · Priority50 % offWas 2 396,421 198,21 DAWas 11 982,085 991,04 DAWas 119,8259,91 DA………
Google AI Studio · Priority50 % offWas 2 396,421 198,21 DAWas 11 982,085 991,04 DAWas 119,8259,91 DA………

Also charged: writing to the cache, at Google AI Studio ↑ 31,20, at Google ↑ 62,41 · a web search 4,66 DA each · audio ↑ 665,67 DA per 1M audio tokens · audio cache read ↑ 33,28 DA per 1M audio tokens · images ↑ 665,67 DA per 1M image tokens.

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.

≈ 2,33 DA per message3 000 DA buys about 1 200 messages

50 % offGoogle has cut its price. Every figure here is the new one.

One message, the ordinary use

1 000 sent1 000 tokens sent× 665,67 per 1M× 665,67 DA per 1M0,67 DA
500 back500 tokens back× 3 328,36 per 1M× 3 328,36 DA per 1M1,66 DA
Total≈ 2,33 DA

Every rate

Meter↑ you send↓ comes back
Text tokens665,67 DA3 328,36 DA
Cached tokens read33,28 DA
Cache-write tokens62,41 DA
Picture tokens665,67 DA
Audio tokens665,67 DA
Cached audio tokens read33,28 DA

per 1M tokens

Web search · 4,66 DA per call

Everyday jobs, priced

Turn a half-hour meeting recording into clean minutes≈ 39,94 DA
Compile a competitor brief from pages found on the live web≈ 39,94 DA
Review product demo clips and note where users struggle≈ 93,19 DA
Summarise a 400-page contract archive and flag anything unusual≈ 282,91 DA
Refactor a large codebase across many files in one pass≈ 931,94 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
google/gemini-4-carbon
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="google/gemini-4-carbon",
    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_pstopseed

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
Gemini
Released
10 Nov 2026
Full API reference

Questions about Gemini 4 Carbon

How much does Gemini 4 Carbon cost in dinars?

About 2,33 DA per message. Was 4,66 DA. ↑ 665,67 DA · ↓ 3 328,36 DA per 1M tokens.

Is Gemini 4 Carbon 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 Gemini 4 Carbon best for?

#1 for SVG drawings · Gemini 4 Carbon takes in text, pictures, sound, video and documents, keeps about 1,000 pages in mind at once, and can write an answer up to 940 pages long. It thinks a question through before answering, so it suits long jobs such as working through a whole codebase, planning a task in many steps, or drafting a lengthy report from mixed source material. Another model in the same family handles the same inputs, but this one can hold a very long written answer in a single piece. It gives back text only, so jobs that need a picture, a sound or a clip in return call for a different kind of model.

Gemini 4 Carbon or Gemini 4 Hydrogen?

Gemini 4 Hydrogen costs 0,58 DA less for the same message.

How do I pay for Gemini 4 Carbon without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Gemini 4 Carbon included, is paid from that balance. No foreign card, no conversion.

Does Gemini 4 Carbon work in Arabic, French or Darja?

Google names no languages for Gemini 4 Carbon. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

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

Is Gemini 4 Carbon open source?

No. Google has not published its weights.

Who makes Gemini 4 Carbon, and when was it released?

Google. Released 10 November 2026.

Other Google models, priced in dinars

See all Google models
Gemini Omni 1.2 FlashGoogle · Nov 5, 2026

This 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.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model
Gemini 3.8 Flash TTSGoogle · Sep 23, 2026

#1 for speech · Gemini 3.8 Flash TTS turns text into speech in 130+ languages with studio-grade acting, regional accents and a voice that stays consistent through long dialogues. It offers prebuilt voices, custom voice personas and voice replication, with about 8 pages of text per request. Pick it for audiobooks, narration and multi-speaker scenes.

30 voices
≈3,02 DAper paragraph read aloud
View model
Gemini Omni 1.1 FlashGoogle · Nov 4, 2026

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.

Searches the webThinks first130 pages at once
≈2,00 DAper message
View model
Gemini 3.5 TranscribeGoogle · Sep 25, 2026

Gemini 3.5 Transcribe turns audio files into text, detecting the language among 85+ and optionally adding the time of each word, speaker labels for as many as eight speakers, and filler-word removal. A request runs up to an hour, or 30 minutes with speakers or timestamps.

≈1,80 DAper minute of audio
View model