Google: Gemini 3.5 Flash Lite

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photo

The total is 42 300,00 DA, due September 3, 2026. Worth a double-check: the handwritten day could read as an 8 instead of a 3.

Reads long documents

supplier-contract.pdf · 120 pages

What penalties do we face if we deliver late?

Three clauses apply: §12.4 charges 0.5% of the order value per late week, capped at 8%; §12.6 lets the buyer cancel after 30 days; §14.2 excludes force-majeure delays.

Structured output

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

google/gemini-3.7-flashText

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.

EndpointPOST /v1/chat/completions

Base URL

https://opendunes.com/api/v1

Model id

google/gemini-3.5-flash-lite

Shell

curl https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.5-flash-lite",
    "messages": [{"role": "user", "content": "In one sentence: why is the sky blue?"}]
  }'

The same request, in your language

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: 1M tokens
Max output: 65.5K tokens
Longest reply: ≈ 49.0K words
Tokenizer: Gemini
Intelligence index: 36.5
Released: 2026-07-21

Full API reference

Questions about Gemini 3.5 Flash Lite

How much does Gemini 3.5 Flash Lite cost in Algerian Dinars?

97,20 DA for the text you send and 810 DA for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,56 DA. You pay for what you actually use: no subscription, no minimum.

How big is Gemini 3.5 Flash Lite's context window?

Gemini 3.5 Flash Lite reads up to 1M tokens in one request, and writes back up to roughly 49,000 words at once.

What can Gemini 3.5 Flash Lite handle?

It reads text, images, video, audio and files and replies with text. It also supports calling your own tools, replying in structured JSON, step-by-step reasoning and streaming its answer as it writes.

Can I use Gemini 3.5 Flash Lite without an international bank card?

Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on Gemini 3.5 Flash Lite or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.

Who makes Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is built by Google, released on Jul 21, 2026. OpenDunes serves it unchanged — same model, same weights, billed in dinars.

Other Google models, priced in dinars

See all Google models

Google: Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

in243 DAout1 215 DAper 1M tokens

google/gemini-3.7-flash:batchText

Google: Gemini 3.7 Flash (batch)

in60,75 DAout303,75 DAper 1M tokens

google/gemini-3.6-flashText

Google: Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

in243 DAout1 215 DAper 1M tokens

google/gemini-3.6-flash:batchText

Google: Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

in121,50 DAout607,50 DAper 1M tokens

google/gemini-3.5-flash-lite:batchText

Google: Gemini 3.5 Flash Lite (batch)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

in48,60 DAout405 DAper 1M tokens

google/gemini-3.1-flash-lite-imageImage

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

81 DA/M input·486 DA/M output

google/gemini-3.1-flash-imageImage

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

162 DA/M input·972 DA/M output

google/gemini-3-pro-imageImage

Google: Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

by GoogleJun 18, 2026131K contextReasoningToolsJSON

648 DA/M input·3 888 DA/M output

by GoogleJun 18, 2026131K contextReasoningToolsJSON

What it can do

Real jobs this model can take on, based on what it can read and how it’s priced.

Read a 300-page contract and answer questions about it

1M-token context · accepts PDFs

Turn a screenshot of a design into working code

understands images

Watch a 20-minute video and tell you what happened

understands video

Transcribe and summarize a recorded meeting

understands audio

Good for

Very long documents — whole books or contract stacks in one request
Mixed media — images, video, audio and files and text together
Tool calling and structured JSON, for building agents
High-volume workloads where cost per reply matters

Not for

Generating images — it replies with text only
Speaking its replies aloud — no audio output
Fine-tuning on your own data — not supported

Also supports

Tool callingStructured JSONStep-by-step reasoningStreamingPrompt cachingFine-tuning

Where your request runs

You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.

Provider	In /M	Out /M	Cache /M	Latency	TPS	Uptime
Google AI Studio	97,20 DA	810 DA	9,72 DA	—	—	99,9 %
Google AI Studio	48,60 DA	405 DA	4,86 DA	—	—	99,9 %
Google AI Studio	174,96 DA	1 458 DA	17,50 DA	—	—	99,9 %
Google	97,20 DA	810 DA	9,72 DA	—	—	99,9 %
Google	48,60 DA	405 DA	4,86 DA	—	—	99,9 %
Google	174,96 DA	1 458 DA	17,50 DA	—	—	99,9 %
Google	106,92 DA	891 DA	10,69 DA	—	—	—

Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.

What it costs

Everyday jobs, priced. Each request charges exactly what it uses — no subscription, no minimum.

Answer a quick question≈ 0,14 DA

Reply to a customer email≈ 0,35 DA

Read an invoice photo and pull out the total≈ 0,34 DA

Translate a full page of text≈ 0,43 DA

Write a one-page draft≈ 0,57 DA

Summarize a 10-page PDF≈ 1,26 DA

Analyze a 120-page contract≈ 7,86 DA

Watch a 20-minute video and tell you what happened≈ 30,13 DA

Top up points

3 000 DA ≈ 5 398 typical replies · the exact charge appears after every request, down to the centime.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Understands images

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photo

The total is 42 300,00 DA, due September 3, 2026. Worth a double-check: the handwritten day could read as an 8 instead of a 3.

Reads long documents

supplier-contract.pdf · 120 pages

What penalties do we face if we deliver late?

Three clauses apply: §12.4 charges 0.5% of the order value per late week, capped at 8%; §12.6 lets the buyer cancel after 30 days; §14.2 excludes force-majeure delays.

Structured output

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.

EndpointPOST /v1/chat/completions

Base URL

https://opendunes.com/api/v1

Model id

google/gemini-3.5-flash-lite

Shell

curl https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.5-flash-lite",
    "messages": [{"role": "user", "content": "In one sentence: why is the sky blue?"}]
  }'

The same request, in your language

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: 1M tokens
Max output: 65.5K tokens
Longest reply: ≈ 49.0K words
Tokenizer: Gemini
Intelligence index: 36.5
Released: 2026-07-21

Full API reference

Questions about Gemini 3.5 Flash Lite

How much does Gemini 3.5 Flash Lite cost in Algerian Dinars?

How big is Gemini 3.5 Flash Lite's context window?

Gemini 3.5 Flash Lite reads up to 1M tokens in one request, and writes back up to roughly 49,000 words at once.

What can Gemini 3.5 Flash Lite handle?

Can I use Gemini 3.5 Flash Lite without an international bank card?

Who makes Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is built by Google, released on Jul 21, 2026. OpenDunes serves it unchanged — same model, same weights, billed in dinars.

Other Google models, priced in dinars

See all Google models

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

in243 DAout1 215 DAper 1M tokens

google/gemini-3.6-flash:batchText

Google: Gemini 3.6 Flash (batch)

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

in121,50 DAout607,50 DAper 1M tokens

google/gemini-3.5-flash-lite:batchText

Google: Gemini 3.5 Flash Lite (batch)

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

in48,60 DAout405 DAper 1M tokens

google/gemini-3.1-flash-lite-imageImage

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

81 DA/M input·486 DA/M output

google/gemini-3.1-flash-imageImage

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

162 DA/M input·972 DA/M output

google/gemini-3-pro-imageImage

Google: Nano Banana Pro (Gemini 3 Pro Image)

by GoogleJun 18, 2026131K contextReasoningToolsJSON