MODELS

Google: Gemini 3.5 Flash

by Google

modellead-sourceopenrouter-modelsgooglegeminigemini-apimultimodalcodingreasoningsource:blog.googlegemini-3.5-flashlarge-contextopenrouter-model

Visit Website Documentation

Overview

Google Gemini 3.5 Flash is a high-efficiency multimodal Gemini API model with Flash-tier speed and cost positioning.

Details

Gemini 3.5 Flash is listed by Google AI for Developers with model code `gemini-3.5-flash`. The official model page describes multimodal inputs, a 1,048,576-token input limit, a 65,536-token output limit, and support for Batch API, caching, code execution, function calling, structured outputs, thinking, and grounding. Google DeepMind’s model card describes it as a natively multimodal reasoning model with up to a 1M-token context window and 64K-token text output. OpenRouter separately describes it as a high-efficiency multimodal model optimized for coding proficiency and parallel agentic execution.

When to Use

Use when you need a Google Gemini API model with multimodal input support and a large 1,048,576-token input limit. Use for applications that need supported Gemini API features such as function calling, structured outputs, code execution, grounding, caching, or Batch API. Evaluate for coding, reasoning, and parallel agentic execution workflows where Flash-tier cost and speed are important.

Getting Started

Review the official Gemini 3.5 Flash model page for model code, token limits, input modes, and supported capabilities.
Check the Gemini Developer API pricing page for current standard, batch, flex, and priority pricing tiers before production use.
Call the model using the `gemini-3.5-flash` model code in the Gemini API and validate behavior with a small test workload.
Review the Google DeepMind model card for intended uses, safety evaluations, benchmark information, and distribution-channel context.

Key Features

•Model code: `gemini-3.5-flash`.
•Multimodal inputs listed in the official Gemini API model page.
•1,048,576 input-token limit and 65,536 output-token limit.
•Supports Batch API, caching, code execution, function calling, structured outputs, thinking, and grounding.
•Official pricing page lists standard paid pricing plus batch, flex, and priority tiers.

Capabilities

•multimodal-input
•large-context
•function-calling
•structured-outputs
•code-execution
•grounding
•batch-api
•caching
•thinking

Last updated May 29, 2026