Gemini 3 Flash Preview

google/gemini-3-flash-preview

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

InputAudioFileImageTextVideo
OutputText
Input / Outputclub$0.53 / $3.18per 1M tokens · USD
Context window1Mtoken
Maximum output65.5Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.53/ 1M token
Cache readUS$0.053/ 1M token
Cache writeUS$0.618333/ 1M token
OutputUS$3.18/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
AudioFileImageTextVideo
Output
Text
Context window
1,048,576 token
Maximum output
65,536 token
Reasoning
high · medium · low · minimal

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Gemini 3 Flash Preview, and who develops it?

Gemini 3 Flash Preview is a model from Google. Its model ID on Vecbase is google/gemini-3-flash-preview. Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

How much does Gemini 3 Flash Preview cost on Vecbase?

For Gemini 3 Flash Preview, the Club plan lists USD 0.53 per 1 million input tokens and USD 3.18 per 1 million output tokens, as of 10/22/2026, 9:25:16 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Gemini 3 Flash Preview’s context window?

Gemini 3 Flash Preview has a context window of 1,048,576 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Gemini 3 Flash Preview?

Gemini 3 Flash Preview can generate up to 65,536 tokens per response. Your API or request settings may set a lower limit.

Can Gemini 3 Flash Preview call tools in an agent workflow?

Yes. Gemini 3 Flash Preview supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Gemini 3 Flash Preview support structured outputs?

Yes. Gemini 3 Flash Preview supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Gemini 3 Flash Preview support?

Gemini 3 Flash Preview accepts Audio, File, Image, Text, and Video and produces Text.

Which providers make Gemini 3 Flash Preview available through Vecbase?

Vecbase offers Gemini 3 Flash Preview through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Gemini 3 Flash Preview?

Use google/gemini-3-flash-preview as the model identifier for Gemini 3 Flash Preview. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for Gemini 3 Flash Preview?

Gemini 3 Flash Preview supports these reasoning levels: high, medium, low, and minimal. Available options depend on your API.

What does an agent need to access Gemini 3 Flash Preview through Vecbase?

To use Gemini 3 Flash Preview, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Gemini 3 Flash Preview?

We do not yet have a confirmed release date for Gemini 3 Flash Preview.

Which models can I compare with Gemini 3 Flash Preview on Vecbase?

You can compare Gemini 3 Flash Preview with Gemini 3.1 Flash-Lite (google/gemini-3.1-flash-lite), Gemini Flash Latest (google/gemini-flash-latest), and Gemini Pro Latest (google/gemini-pro-latest). Check their capabilities and prices to find the best fit for your task.