Gemini 3.6 Flash is a Flash-tier model in the Gemini API, available as gemini-3.6-flash. Google's model page lists it as stable and describes it as a previous-generation Flash model that remains available for production, balancing speed and multimodal capability. Google's models overview shows Gemini 3.8 Flash (gemini-3.8-flash) as the newer stable Flash. If you are starting a new project, compare the two before committing.
Key features
- Limits: per the model page, input up to 1,048,576 tokens and output up to 65,536 tokens.
- Inputs and outputs: text, image, video, audio and PDF in; text out.
- Tooling: caching, code execution, file search, function calling, Google Maps grounding, Search grounding, structured outputs, thinking, URL context, and computer use in preview.
- Consumption options: Batch API, Flex inference and Priority inference.
- Not supported: audio generation, image generation and the Live API.
- Last updated: Google's page shows July 2026.
Use cases
- Multimodal analysis of documents, audio and video with text output.
- Agent workflows that use function calling, search grounding or URL context.
- Production systems already tuned to 3.6 Flash that do not yet need to move.
Pricing and availability
Status: stable, described as a previous-generation Flash model, on Google's models page, checked on 2026-10-29. Google shows no deprecation date. The model page does not list prices and points to the pricing page, so check Google's Gemini API pricing for current rates.
Getting started
- Get a Gemini API key from Google AI Studio.
- Use
gemini-3.6-flashas the model id. - Run the same prompts against
gemini-3.8-flashand compare quality, latency and cost. - Pick one and pin it, then recheck Google's models page for status changes.
FAQ
Is Gemini 3.6 Flash still available?
Yes. Google lists gemini-3.6-flash as stable and as a previous-generation Flash model that remains available for production.
What is newer than Gemini 3.6 Flash?
Google's models page lists Gemini 3.8 Flash (gemini-3.8-flash) as the new stable Flash. It does not call it an official successor.
What is the context window?
An input limit of 1,048,576 tokens and an output limit of 65,536 tokens.
Does it generate images or audio?
No. Output is text only, and image generation, audio generation and the Live API are not supported.
Alternatives
- Gemini 3.7 Flash: another Flash release in the catalog.
- Gemini 3.5 Flash: an earlier Flash release.
- Gemini 3.1 Flash-Lite: the lower-cost Lite tier.
Conclusion
Gemini 3.6 Flash is a stable, production-ready multimodal model with large limits, now positioned as the previous generation. Keep it where it works and test the newer Flash for new builds. See the model page and the models category.
Sources
- Websitehttps://ai.google.dev/gemini-api/docs/models
- Social Mediahttps://x.com/GoogleAI
Comments
No comments yet. Be the first to comment!