OpenLuxGemini 3 Flash (preview) API
Gemini 3 Flash (preview) is the lowest-cost Gemini option on OpenLux: $0.0368 per million tokens — 92% below list — for high-concurrency workloads that still need vision and tool calling.
Pay-as-you-go rate
$0.0368 / 1M tokens
-92% vs official list pricing. Billed in USD, metered per request with real-time cost in the console.
Access
One OpenLux key and the OpenAI-compatible endpoint: set base_url to https://openlux.lol/v1 and pass gemini-3-flash-preview as the model.
Get started
Create a key in the console, then follow the five-minute docs for streaming, tools and error codes.
What Gemini 3 Flash (preview) delivers
Preview releases give early access to Google’s newest Flash generation at rates that undercut even the stable Flash line. It suits experimentation, load tests and cost-sensitive pipelines where a preview lifecycle is acceptable.
The model keeps the same multimodal feature set: text and image input, streaming and function calling on the OpenAI-compatible endpoint. Code written against it moves to stable Flash models with a model-field change.
Watch the model catalogue for graduation to general availability — rates and discounts for every model are published there, so a preview becoming stable never changes your integration.
Call Gemini 3 Flash (preview) in minutes
Every OpenLux model speaks the OpenAI protocol. Reuse your existing SDKs and replace two values: the base URL and the API key.
cURL
curl https://openlux.lol/v1/chat/completions \
-H "Authorization: Bearer $OPENLUX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-flash-preview",
"messages": [{"role": "user", "content": "Tag these 20 product titles with a category and a confidence score between 0 and 1."}]
}'Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
api_key="sk-openlux-...",
base_url="https://openlux.lol/v1",
)
resp = client.chat.completions.create(
model="gemini-3-flash-preview",
messages=[{"role": "user", "content": "Tag these 20 product titles with a category and a confidence score between 0 and 1."}],
)
print(resp.choices[0].message.content)Node.js (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPENLUX_API_KEY,
baseURL: "https://openlux.lol/v1",
});
const resp = await client.chat.completions.create({
model: "gemini-3-flash-preview",
messages: [{ role: "user", content: "Tag these 20 product titles with a category and a confidence score between 0 and 1." }],
});
console.log(resp.choices[0].message.content);Where Gemini 3 Flash (preview) fits
Lowest unit cost
$0.0368 per 1M tokens — the cheapest text model in the Gemini family on OpenLux.
Vision input
Image understanding at preview pricing for extraction and classification jobs.
Tools and functions
Function calling for pipelines and assistants built on Flash.
Preview lifecycle
Early access to the newest Flash generation; model availability follows Google upstream.
High-concurrency chat
Consumer-scale chat where per-message cost is the deciding factor.
Experiments and evaluation
Run large evaluation sets and prompt experiments without budget anxiety.
Cost-sensitive pipelines
Bulk tagging, translation and cleanup jobs at the lowest available rate.
How gemini-3-flash-preview is priced on OpenLux
Gemini 3 Flash (preview) is metered pay as you go at $0.0368 / 1M tokens (-92% vs official rates). There is no subscription requirement for API access: top up a balance, call the model, and see the cost of every request in the console.
| Model | Provider | Rate | Discount |
|---|---|---|---|
| gemini-3-flash-preview (this model) | $0.0368 / 1M tokens | -92% | |
| gemini-3.8-flash | $0.0551 / 1M tokens | -92% | |
| gemini-3.1-flash-image-preview | $0.0122 / request | -92% | |
| deepseek-v4 | DeepSeek | $0.0613 / 1M tokens | -90% |
Rates follow official provider pricing and are shown in USD. See the full model catalogue and pricing plans for credit allowances.
Gemini 3 Flash (preview) questions
How much does gemini-3-flash-preview cost?
$0.0368 per 1 million tokens, 92% below list pricing, metered pay as you go like every model on OpenLux.
How do I call a preview model?
Exactly like a stable model: set the model field to gemini-3-flash-preview on /v1/chat/completions. Preview models are called through the same endpoint, key and billing.
What does "preview" mean in practice?
It is early access to the newest Flash generation before general availability. Upstream may update or rename the model, so pin stable models for long-lived production paths and use preview for evaluation and cost-sensitive traffic.
Does it support vision and tools?
Yes — image input, streaming and function calling are supported on the same OpenAI-compatible endpoint.
Start calling Gemini 3 Flash (preview) today
Create an OpenLux key and send your first request in minutes. Compare Gemini 3 Flash (preview) with the rest of the catalogue on the same endpoint and the same bill.