Vertex AI

Vertex AI: Gemini 3 Flash (Preview, Vertex)

preview

Gemini 3 Flash (Preview, Vertex) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

gemini-3-flash-previewgemini-3released Dec 17, 2025
ProviderQuick start
Context
1.0M
tokens
Max output
65.5K
tokens
Input
$0.50
per 1M
Output
$3.00
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Google
Google
1.0M$0.50$3.00
Vertex AI
Vertex AI
1.0M$0.50$3.00

Pricing

ItemPriceUnit
Input$0.50per 1M tokens
Output$3.00per 1M tokens
Cache read$0.050per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
gemini-3-flash-preview
Family
gemini-3
Status
preview
Knowledge
-
Released
Dec 17, 2025
Gateway Config
API
v1
Auth
GOOGLE_APPLICATION_CREDENTIALS
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@vertex-ai/gemini-3-flash-preview",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}
Chat completions
https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/chat/completions
Model
gemini-3-flash-preview
Auth env
GOOGLE_APPLICATION_CREDENTIALS

Gemini 3 Flash (Preview, Vertex) FAQ

How much does the Gemini 3 Flash (Preview, Vertex) API cost?

Through Vertex AI, Gemini 3 Flash (Preview, Vertex) costs $0.50 per 1M input tokens and $3.00 per 1M output tokens.

What is the context window of Gemini 3 Flash (Preview, Vertex)?

Gemini 3 Flash (Preview, Vertex) accepts up to 1.0M tokens of context and returns up to 65.5K output tokens on Vertex AI.

Which providers offer Gemini 3 Flash (Preview, Vertex)?

Gemini 3 Flash (Preview, Vertex) is available from Google and Vertex AI. Everstack can route between them with automatic fallback when one is unavailable.

What can Gemini 3 Flash (Preview, Vertex) do?

Gemini 3 Flash (Preview, Vertex) supports chat, function calling, image input and reasoning. It accepts text, image, video, audio and PDF input.

How do I call Gemini 3 Flash (Preview, Vertex) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @vertex-ai/gemini-3-flash-preview. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.