by GoogleReleased 3 April 2026
Gemma 4 26B A4B is a model you can download and run yourself that uses only a small part of itself on each word, so it answers like a small model while aiming near the 31B in quality. It reads text and images, thinks on request, uses your tools, and keeps about 256 pages in mind at once. Pick it for fast work at high volume.
You pay for what each request uses. No subscription, no minimum.
25 % offNextBit 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 | 22,47 DA | 74,89 DA |
| Cached tokens read | 12,48 DA |
per 1M tokens
15 companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Cache read | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
| Darkbloom | 13,31 DA | 49,93 DA | 3,33 DA | … | … | … |
| PrimeIntellect | 15,98 DA | 47,60 DA | 7,99 DA | … | … | … |
| DekaLLMAsia | 19,97 DA | 109,84 DA | 13,31 DA | … | … | … |
| NextBit25 % offEurope | … | … | … | |||
| AkashML | 23,30 DA | 79,88 DA | 15,31 DA | … | … | … |
| DeepInfraUnited States | 23,30 DA | 113,16 DA | none | … | … | … |
| Makora | 26,63 DA | 33,28 DA | 15,31 DA | … | … | … |
| Io Net | 29,96 DA | 103,18 DA | 13,65 DA | … | … | … |
| CoreWeaveUnited States | 33,28 DA | 99,85 DA | 16,64 DA | … | … | … |
| Cloudflare | 33,28 DA | 99,85 DA | 16,64 DA | … | … | … |
| VeniceUnited States | 43,27 DA | 133,13 DA | 16,64 DA | … | … | … |
| Parasail | 43,27 DA | 133,13 DA | 16,64 DA | … | … | … |
| Novita | 43,27 DA | 133,13 DA | none | … | … | … |
| SiliconFlowUnited States | 46,60 DA | 133,13 DA | 16,64 DA | … | … | … |
| 49,93 DA | 199,70 DA | none | … | … | … |
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 LabTurn this customer email into JSON with intent, urgency and order_id.
customer-email.txtTry 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="google/gemma-4-26b-a4b-it",
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_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_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_choiceOther
Also accepted by this model.
max_completion_tokensAbout 0,060 DA per message. Was 0,080 DA. ↑ 22,47 DA · ↓ 74,89 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
Gemma 4 26B A4B is a model you can download and run yourself that uses only a small part of itself on each word, so it answers like a small model while aiming near the 31B in quality. It reads text and images, thinks on request, uses your tools, and keeps about 256 pages in mind at once. Pick it for fast work at high volume.
Gemma 4 31B costs 0,070 DA more for the same message.
Deposit dinars with your Edahabia or CIB card. Every model, Gemma 4 26B A4B included, is paid from that balance. No foreign card, no conversion.
Google says Gemma 4 supports 35+ languages out of the box and was pre-trained on over 140. Arabic, French and Darja are not named.
It reads text, images and video. Up to 262K tokens in one request, about 260 pages. It writes up to 177 000 words at once.
Yes, its weights are public. Open weights on Hugging Face
Google. Released 3 April 2026. It knows the world up to January 2025.
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.
#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.
Nano Banana 2, Google's 3.1 Flash Image model, generates and edits images from a written description and reference pictures, returning images with text. It outputs up to 4K, adds very tall and very wide shapes such as 1:8, and renders text in other languages better. Pick it for production batches of ads, banners and edits.
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.
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
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.
Knows events up to Jan 2025
Read on huggingface.co.
Run a private assistant on your own server
Uses your tools
Read a scanned form and return its fields as JSON
Images · Fills your JSON
Describe what happens in a short video
Video