Text Generation Model

Gemini 3.6 Flash

Gemini 3.6 Flash is a text and image understanding model from Google with a 1,048,576-token context window.

Start Building with Gemini 3.6 Flash View All Models

Publisher

Google

TypeText

Context Window1,048,576 tokens

ReleasedJuly 2026

Input$0.75/MTok

Output$3.75/MTok

LARGE CONTEXTREASONINGTOOLS

Try Gemini 3.6 Flash →

About Gemini 3.6 Flash

Large-context reasoning with tool use

Gemini 3.6 Flash is a multimodal text generation model developed by Google, released in July 2026. It accepts both text and image inputs and supports a context window of 1,048,576 tokens, allowing it to process very long documents or extended conversation histories in a single request. The model also exposes a configurable thinking level, enabling users to adjust how much internal reasoning the model applies before generating a response.

Gemini 3.6 Flash is designed for tasks that benefit from large context capacity, structured reasoning, and tool integration. Its maximum response size of 65,536 tokens makes it suitable for generating lengthy outputs such as detailed reports, code files, or multi-step analyses. The tools input type means it can be connected to external functions or APIs, making it a practical choice for agentic workflows and applications that require the model to take actions beyond text generation.

Capabilities

What Gemini 3.6 Flash supports

Large Context Window

Processes up to 1,048,576 tokens in a single request, enabling analysis of long documents, codebases, or extended conversation histories without truncation.

Configurable Reasoning

Exposes a Thinking Level selector that lets users control how much internal reasoning the model performs before producing a response.

Tool Use

Accepts a tools input that connects the model to external functions or APIs, supporting agentic and multi-step workflows.

Image Understanding

Accepts image inputs alongside text, allowing the model to analyze, describe, or reason about visual content within a prompt.

Long-Form Output

Supports a maximum response size of 65,536 tokens, making it suitable for generating detailed reports, lengthy code files, or extended analyses.

Ready to build with Gemini 3.6 Flash?

Get Started Free

FAQ

Common questions about Gemini 3.6 Flash

What is the context window size for Gemini 3.6 Flash?

Gemini 3.6 Flash has a context window of 1,048,576 tokens, which allows it to process very long documents or extended conversations in a single request.

What is the maximum response length this model can produce?

The model supports a maximum response size of 65,536 tokens per output.

Does Gemini 3.6 Flash support image inputs?

Yes, the model accepts image inputs in addition to text, making it capable of multimodal tasks.

What does the Thinking Level setting do?

The Thinking Level is a configurable input that controls how much internal reasoning the model applies before generating its response. Adjusting it can affect response depth and latency.

Can Gemini 3.6 Flash use external tools or APIs?

Yes, the model includes a tools input type that allows it to be connected to external functions or APIs, enabling agentic and multi-step task execution.

What is the pricing for Gemini 3.6 Flash?

Pricing information for Gemini 3.6 Flash has not been published in the available metadata. Check the MindStudio platform or Google's official pricing pages for current rates.

Resources