by ~googleReleased 27 April 2026
#5 for gamesGemini 3.8 Flash takes text, images, video, audio and PDFs, keeps about 1,000 pages in mind at once, and returns text up to 65 pages long, with low, medium and high thinking levels. Google rates it the strongest Flash model for long software-engineering runs, assistants that act on their own and business workflows.
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 | 249,63 DA | 1 248,13 DA |
| Cached tokens read | 24,96 DA | |
| Cache-write tokens | 13,87 DA | |
| Picture tokens | 249,63 DA | |
| Audio tokens | 249,63 DA | |
| Cached audio tokens read | 24,96 DA |
per 1M tokens
Web search · 4,66 DA per call
One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.
| Provider | ↑ Sent | ↓ Back | Latency | Throughput | Uptime |
|---|---|---|---|---|---|
| Google: Gemini Flash Latest | 249,63 DA | 1 248,13 DA | … | … | … |
Also charged: cache write ↑ 13,87 DA per 1M tokens · audio ↑ 249,63 DA per 1M audio tokens · audio cache read ↑ 24,96 DA per 1M audio tokens · images ↑ 249,63 DA per 1M image tokens · web search 4,66 DA per search.
You pay the price of the provider that served your request. 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/gemini-flash-latest",
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_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_choiceAbout 0,87 DA per message. ↑ 249,63 DA · ↓ 1 248,13 DA per 1M tokens.
No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.
#5 for games · Gemini 3.8 Flash takes text, images, video, audio and PDFs, keeps about 1,000 pages in mind at once, and returns text up to 65 pages long, with low, medium and high thinking levels. Google rates it the strongest Flash model for long software-engineering runs, assistants that act on their own and business workflows.
Deposit dinars with your Edahabia or CIB card. Every model, Gemini Flash Latest included, is paid from that balance. No foreign card, no conversion.
Google lists 101 languages the Gemini models understand and answer in, Arabic and French among them. Darja is not named.
It reads text, images, video, audio and PDFs. Up to 1M tokens in one request, about 1 000 pages. It writes up to 49 000 words at once.
No. ~google has not published its weights.
~google. Released 27 April 2026.
#1 for games · Gemini 4 Argon takes text, images, video, audio and PDFs, keeps about 1,000 pages in mind, and answers in text up to about 1,000 pages long, with low, medium and high thinking. Google calls it its top model for reasoning. Pick it for complex software engineering, hard math and science, and assistants that carry out many steps on their own.
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
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 No.
Read on ai.google.dev.
Run an agent that calls your APIs
Uses your tools · Thinks first
Read a long PDF and return its key fields as JSON
Files · Fills your JSON
Summarise a recorded meeting
Audio