How much does Gemini 3.5 Flash cost?

Gemini 3.5 Flash is listed at $1.5/1M input tokens, $0.15/1M cached input tokens, and $9/1M output tokens.

What is the context window for Gemini 3.5 Flash?

Gemini 3.5 Flash supports a context window of 1.05M tokens in Sim. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

What capabilities does Gemini 3.5 Flash support?

Gemini 3.5 Flash supports the following capabilities in Sim: Temperature 0-2, Tool choice, Structured outputs, Thinking minimal, low, medium, high.

What is Gemini 3.5 Flash best used for?

Best for reasoning-heavy tasks that need more deliberate model control. When used in a Sim workflow, it can be selected in any Agent block from the model picker.

Back to Google

Google model

Gemini 3.5 Flash

Name: Gemini 3.5 Flash
Brand: Google
SKU: gemini-3.5-flash

Gemini 3.5 Flash is a Google model tracked in Sim. It supports a 1.05M token context window. Pricing starts at $1.5/1M input tokens and $9/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs. Best for reasoning-heavy tasks that need more deliberate model control.

Build with this model All Google models

Input price$1.5/1M

Cached input$0.15/1M

Output price$9/1M

Context window1.05M

Max outputNot published

ProviderGoogle

UpdatedJul 9, 2026

Best forBest for reasoning-heavy tasks that need more deliberate model control.

Temperature0 to 2

Reasoning effortNot supported

VerbosityNot supported

Thinking levelsminimal, low, medium, high (default: medium)

Structured outputsSupported

Tool choiceSupported

Computer useNot supported

Deep researchNot supported

Memory supportSupported

Max output tokensNot published

Frequently asked questions

Gemini 3.5 Flash is a Google model available in Sim. Gemini 3.5 Flash is a Google model tracked in Sim. It supports a 1.05M token context window. Pricing starts at $1.5/1M input tokens and $9/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.