Gemini 3.6 Flash
Google· released 21 Jul 2026
google/gemini-3.6-flash- Input / 1M tokens
- $0.75
- Output / 1M tokens
- $3.75
Longest answer: 66K tokens
About
Gemini 3.6 Flash is Google’s model for coding, agentic workflows, and web and app development. Its summary describes it as designed to produce polished outputs with fewer unnecessary edits. It accepts text, images, video, files, and audio, while producing text. Tool use and reasoning are supported, and vision is listed. The context window is 1,048,576 tokens, with a maximum output of 65,536 tokens. Input costs $0.75 per 1M tokens and output costs $3.75 per 1M tokens. Its model ID is google/gemini-3.6-flash, and its family is google. Google released it on 2026-07-21. For teams assessing a model across development workflows, its listed use cases and varied input types are relevant; the input and output rates and output limit are also part of the fit.
Who it is for
It suits teams building coding, agentic, web, or app development workflows. Its image, video, file, and audio inputs may also fit workflows that combine those materials with text.
What is good
- Built for coding and agentic workflows.
- Accepts text, image, video, file, and audio.
- Supports tools, vision, and reasoning.
- 1,048,576-token context window.
What to know first
- Output is limited to 65,536 tokens.
- Input costs $0.75 per 1M tokens.
- Output costs $3.75 per 1M tokens.
Verdict
Gemini 3.6 Flash combines development-oriented uses with broad input modalities and a large context window. Its 65,536-token output limit and per-token rates are worth considering when matching it to a workload.
Details
- Lab
- Googleopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.75 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $3.75 / 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
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-3.6-flash· checked 3 Oct 2026