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.
Gemini 4 Carbon (batch)
Newby 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.
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.
Also charged: writing to the cache ↑ 62,41 · a web search 4,66 DA each · audio ↑ 332,84 DA per 1M audio tokens · audio cache read ↑ 16,64 DA per 1M audio tokens · images ↑ 332,84 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.
50 % offGoogle has cut its price. Every figure here is the new one.
One message, the ordinary use
Every rate
| Meter | ↑ you send | ↓ comes back |
|---|---|---|
| Text tokens | 332,84 DA | 1 664,18 DA |
| Cached tokens read | 16,64 DA | |
| Cache-write tokens | 62,41 DA | |
| Picture tokens | 332,84 DA | |
| Audio tokens | 332,84 DA | |
| Cached audio tokens read | 16,64 DA |
per 1M tokens
Web search · 4,66 DA per call
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.
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="google/gemini-4-carbon:batch",
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_pstopseedReasoning
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_choiceLimits
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
Questions about Gemini 4 Carbon (batch)
How much does Gemini 4 Carbon (batch) cost in dinars?
About 1,16 DA per message. Was 2,32 DA. ↑ 332,84 DA · ↓ 1 664,18 DA per 1M tokens.
Is Gemini 4 Carbon (batch) 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 (batch) 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.
How do I pay for Gemini 4 Carbon (batch) without an international card?
Add credit in dinars with your Edahabia or CIB card. Every model, Gemini 4 Carbon (batch) included, is paid from that balance. No foreign card, no conversion.
Does Gemini 4 Carbon (batch) work in Arabic, French or Darja?
Google names no languages for Gemini 4 Carbon (batch). 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 (batch) open source?
No. Google has not published its weights.
Who makes Gemini 4 Carbon (batch), and when was it released?
Google. Released 10 November 2026.
Other Google models, priced in dinars
See all Google models#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.
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.
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.