Skip to main content
Field Guide

Gemini 3.5 Flash API Review (2026): Deprecated and Replaced by 3.6 Flash

Best for: Developers who still call gemini-3.5-flash and need to know what changed and which model to move to.

Start here

Decision summary

Who it’s for, what it costs, and the catch — answered up top.

Best forDevelopers who still cal…Primary use case
Plan fitNot listed on Goog…Free tier available
Watch outSee caveatsMain caveat

Bottom line

Deprecated 8 October 2026: Google routes gemini-3.5-flash calls to Gemini 3.6 Flash. Gemini 3.8 Flash is the Flash model it now highlights.

Research-based — not hands-on tested. Our scores are editorial judgements compiled from vendor documentation, published pricing and independent user reports. How we review.

Gemini 3.5 Flash at a Glance

Gemini 3.5 Flash (gemini-3.5-flash) is a Google model that was released on 19 May 2026 and deprecated on 8 October 2026. Google’s model page now describes it as “a deprecated earlier-generation Flash model”. This page records what Google has published about it, what happens to API calls that still name it, and which model to use instead. Every figure below was read from the Google page linked beside it on 24 October 2026.

What Google Changed on 8 October 2026

Google’s Gemini API release notes for 8 October 2026 state: “gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash.”

  • The model can no longer be selected in Google AI Studio.
  • API requests to gemini-3.5-flash are routed automatically to gemini-3.6-flash.
  • Google tells developers to update the model string to gemini-3.6-flash (or gemini-3.8-flash).
  • The deprecations page lists the shutdown date as N/A and says the endpoint is not shutting down.

Because of the routing, code that still names gemini-3.5-flash keeps working but is answered by Gemini 3.6 Flash. Google’s what’s-new page calls 3.6 Flash a direct replacement with “reduced token usage and lower output pricing”. Set the model string you intend to run.

Specifications Google Lists for Gemini 3.5 Flash

From Google’s Gemini 3.5 Flash model page, whose “Latest update” field reads May 2026:

Property Google’s listing
Model code gemini-3.5-flash
Input Text, image, video, audio and PDF
Output Text
Input token limit 1,048,576
Output token limit 65,536
Supported Caching, code execution, computer use (preview), file search, function calling, grounding with Google Maps, search grounding, structured outputs, thinking, URL context, Batch API, Flex inference, Priority inference
Not supported Audio generation, image generation, Live API

Pricing

Google’s pricing page has no gemini-3.5-flash row as of 24 October 2026, so this page quotes no price for it. For current Gemini Flash prices, use that page or the AI model comparison.

Which Model to Use Now

Google names two targets. gemini-3.6-flash is the direct replacement; the Gemini 3.6 Flash review covers how it behaves. gemini-3.8-flash reached general availability on 2 September 2026, and Google’s what’s-new page calls it “our latest and most intelligent Flash model”. For a new project, 3.8 Flash is the Flash model Google currently highlights.

Sources

All pages were read on 24 October 2026.

Who it’s for

Ideal for: Developers who still call gemini-3.5-flash and need to know what changed and which model to move to.