Google: Gemini 3 Flash Preview

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

gemini-3-flash-preview

AvailableGoogleChatCached input 90% lessPreview

Input / Output-50%: $0.50 / $3.00$0.25 / $1.50
Context: 1M
Released: Dec 17, 2025
Max output: 64K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

About Gemini 3 Flash Preview

Gemini 3 Flash is Google's first Flash-tier model of the Gemini 3 generation, offered in preview. Google describes it as frontier-class performance at a fraction of the cost of larger models. It takes text and images, calls tools, returns structured JSON, and supports context caching. Later 3.x Flash releases have since replaced it as the default choice for new projects.

Where it works well

Accepts text and images in one request, so a single call can read a screenshot and answer about it.
Structured JSON output against a schema keeps downstream parsing simple.
Tool calling lets it drive search or database steps inside an agent loop.
Context caching reduces repeated work when many requests share a long prefix.

When to choose another model

It is a preview release, so behavior and availability can change before a stable version appears.
Newer Flash versions such as 3.8 Flash are the better start for new work on coding and long agent runs.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textGemini API

POST/v1beta/models/gemini-3-flash-preview:generateContent

API format:

curl "https://api.tokenlab.sh/v1beta/models/gemini-3-flash-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxx" \
  -d '{
    "contents": [
      {"role": "user", "parts": [{"text": "Hello!"}]}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $0.50 / Output $3.00 / Cache read $0.05
Verified price: Input $0.25 / Output $1.50 / Cache read $0.025
Discount: -50%

Prompt cache pricing

Cache read

Official price: $0.05
Verified price: $0.025
Discount: -50%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.014/search
Verified price: $0.007/search
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $0.50 / Output $3.00 / Cache read $0.05	Input $0.25 / Output $1.50 / Cache read $0.025	-50%
Prompt cache pricing
Cache read	$0.05	$0.025	-50%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.014/search	$0.007/search	-50%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 11:10 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Gemini 3 Flash Preview in Console with a prompt ready to edit or send.

Help me try gemini-3-flash-preview with a short message at /v1beta/models/gemini-3-flash-preview:generateContent. Show the reply, latency, and cost.

Use cases

Best for

Reasoning
Vision

Multimodal triage
Classify uploaded screenshots, receipts, or photos and return a fixed JSON record for each one.
Lightweight agents
Run a search-and-answer assistant that calls two or three tools per turn without needing a Pro-class model.
Document question answering
Put a shared policy document in a cached prefix and answer many short questions against it.
Evaluation of newer models
Keep it as a baseline when measuring what later Flash versions change for your own prompts.

Prompt examples

Look at this screenshot of an error dialog and return JSON with the app name, the error code, and a likely cause.

Using the search tool, find the current opening hours for these three clinics and summarize them in a table.

Classify each support email below as billing, bug, or feature request and give a one-line reason.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Gemini 3 Flash Preview?

It is the preview of Google's Gemini 3 Flash model, a lower-cost multimodal model for chat, tools, and structured output. The preview label means Google may change it before release, so pin it only where that risk is acceptable.

Does it support images?

Yes. It accepts images alongside text in the same request and answers about them, which suits screenshot reading, photo classification, and chart questions. It returns text only.

Can it return JSON?

Yes. It supports a response schema, so you can ask for output that matches a fixed structure instead of free text. This is the usual way to feed its answers into a database or another service.

Should I use it for new projects?

Probably not as a first pick. Google now lists newer Flash versions, including 3.8 Flash, as stable and recommends them for new work. Use this preview mainly to keep an existing integration running.

How much does Gemini 3 Flash Preview cost?

On TokenLab, Gemini 3 Flash Preview costs Input $0.25 / Output $1.50 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Gemini 3 Flash Preview?

Gemini 3 Flash Preview accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens in one response.

Which endpoint should Gemini 3 Flash Preview use?

Use https://api.tokenlab.sh/v1beta/models/gemini-3-flash-preview:generateContent for Gemini 3 Flash Preview. The request example below shows the matching code shape.

Which operations does Gemini 3 Flash Preview support?

Gemini 3 Flash Preview supports Text to text. Select an operation above to see its endpoint and request example.