by GoogleReleased 2 September 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.
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 | 249,63 DA | 1 248,13 DA |
| Cached tokens read | 24,96 DA | |
| Cache-write tokens | 13,87 DA | |
| Picture tokens | 274,59 DA | |
| Audio tokens | 249,63 DA | |
| Cached audio tokens read | 24,96 DA |
per 1M tokens
Web search · 4,66 DA per call
Two 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 |
|---|---|---|---|---|---|---|
| Google AI Studio50 % off | … | … | … | |||
| Google50 % off | … | … | … | |||
Also charged: writing to the cache ↑ 13,87 · a web search 4,66 DA each · audio ↑ 274,59 DA per 1M audio tokens · audio cache read ↑ 27,46 DA per 1M audio tokens · images ↑ 274,59 DA per 1M image tokens.
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/gemini-3.8-flash",
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 0,96 DA per message. Was 1,92 DA. ↑ 274,59 DA · ↓ 1 372,95 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 3.8 Flash 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 2 September 2026. It knows the world up to March 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.
#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
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.
Knows events up to Mar 2026
Read on ai.google.dev.
Fix a bug across several files of a codebase
Thinks first
Run an agent that calls your order and stock APIs
Uses your tools
Read a 300-page tender and list every deadline as JSON
Files · Fills your JSON