Gemini 3.5 Flash Lite

Google· released 21 Jul 2026

google/gemini-3.5-flash-lite

Input / 1M tokens: $0.3
Output / 1M tokens: $2.5

Context window1M tokens

Longest answer: 66K tokens

reads textreads imagereads videoreads filereads audiotool callingvisionreasoning

About

Gemini 3.5 Flash Lite is a Google model for focused tasks in multi-agent workflows. Its stated emphasis is high efficiency and upgraded agentic capabilities, with subagents as a specific use case. It accepts text, images, video, files, and audio, and produces text. The model has a 1,048,576-token context window and a maximum output of 65,536 tokens. Tools, vision, and reasoning are supported. The model ID is google/gemini-3.5-flash-lite. Input costs $0.30 USD per 1M tokens and output costs $2.50 USD per 1M tokens. Google is both the maker and lab. It was released on 2026-07-21. These details make its input breadth and long context central considerations when fitting it into a workflow; the listed output remains text. The official listing is https://openrouter.ai/google/gemini-3.5-flash-lite.

Who it is for

It suits teams assigning focused subtasks to agents within larger workflows. Its image, video, file, and audio inputs may fit pipelines that need more than text input.

What is good

Accepts text, image, video, file, and audio inputs
Context window is 1,048,576 tokens
Tools, vision, and reasoning are supported
Maximum output is 65,536 tokens

What to know first

Output is text only
Output costs $2.50 USD per 1M tokens

Verdict

Gemini 3.5 Flash Lite is oriented toward focused subagent work and accepts several input types. Consider its text-only output and per-token input and output rates when selecting it for a workflow.

Details

Lab: Googleopenrouter.ai · 3 Oct 2026
Context: 1,049Kopenrouter.ai · 3 Oct 2026
Input price: $0.3 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $2.5 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 65,536 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, image, video, file, audioopenrouter.ai · 3 Oct 2026
Open weights: Noopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash ctx262KinFreeoutFree inclusionAI Apodex 1.1 Mini (free) ctx262KinFreeoutFree Apodex Pareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiased GPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI GPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI Claude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Google Models: Pricing per 1M Tokens and Context (2026)43 listed

Sources

openrouter.ai/google/gemini-3.5-flash-lite· checked 3 Oct 2026