Gemini 3.6 Flash

Important: Gemini 3.6 Flash will be retired on November 19, 2026. Upgrade to Gemini 3.8 Flash to avoid service disruptions.

Gemini 3.6 Flash is optimized for multi-step orchestration, full-stack code refactoring, and general reasoning. It improves on many key areas critical to the Flash line of models.

Improvements from previous Flash models include:

• Improved token efficiency over Gemini 3.5 Flash. 3.6 Flash uses less tokens and completes multi-step workflows in fewer turns.
• Improved code generation with lower compile-failure and revision rates across building, prototyping, and IDE agent environments.
• Reduces action bias by resolving read-only diagnostic tasks without making unsolicited edits.
• Improved multimodal reasoning with respect to chart interpretation, visual blueprint conversion, and multi-element web layout generation.

Flash includes the following potentially breaking changes when compared to previous Gemini models:

• Custom values for parameters like temperature, top-K, and top-P aren't supported. If you set a custom value for these parameters, that value will be ignored.
• Custom values for frequency and presence penalty parameters aren't supported. Setting a custom value for these parameters will throw an error.
• API requests where the last input turn has a role of Model aren't supported. The following kinds of requests will return an error:
  • When using the Interactions API: Requests where the last object in the input array has "type": "model_output".
  • When using the GenerateContent API: Requests where the last object in the contents array has "role": "model".

Try in Agent Studio Deploy example app Developer guide Pricing

Note: "Deploy example app" requires a Google Cloud project with billing and Agent Platform API enabled.

Model ID	gemini-3.6-flash
Modalities	description Text Input and output photo Image Input only mic Audio Input only videocam Video Input only
Token limits	Context window	1,048,576
	Maximum output tokens	65,536
Capabilities	Thinking Supported System instructions Supported Structured output Supported Context caching Implicit context caching, explicit context caching Supported RAG Engine Supported Tuning Not supported URL context Supported Agentic video understanding Preview feature Supported
Tools	Grounding Google Search, Google Maps Supported Code execution Supported Function calling Supported Computer use Preview feature Supported
APIs	GenerateContent API Supported Interactions API Preview feature Supported Gemini Live API Not supported Count Tokens API Supported Chat Completions API Supported
Consumption options	Provisioned Throughput Supported Batch inference Supported Pay-as-you-go Standard PayGo with Usage Tiers, Flex PayGo, Priority PayGo Supported Fixed quota Not supported
Technical specifications	Image	Maximum images per prompt: 3,000 Maximum file size per file for inline data or direct uploads through the console: 7 MB Maximum file size per file from Google Cloud Storage: 30 MB Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Text	Maximum number of files per prompt: 3,000 Maximum number of pages per file: 3,000 Maximum file size per file for the API or Cloud Storage imports: 50 MB(application/pdf) or 7 MB(text/plain) Maximum file size per file for direct uploads through the console: 7 MB Supported MIME types: application/pdf, text/plain
	Video	Maximum video length (with audio): Approximately 45 minutes Maximum video length (without audio): Approximately 1 hour Maximum number of videos per prompt: 10 Supported MIME types: video/x-flv, video/quicktime, video/mpeg, video/mpegs, video/mpg, video/mp4, video/webm, video/wmv, video/3gpp
	Audio	Maximum audio length per prompt: Approximately 8.4 hours, or up to 1 million tokens Maximum number of audio files per prompt: 1 Supported MIME types: audio/x-aac, audio/flac, audio/mp3, audio/m4a, audio/mpeg, audio/mpga, audio/mp4, audio/ogg, audio/pcm, audio/wav, audio/webm
	Parameter defaults	Temperature: 1.0 topP: 0.95 topK: 64 Frequency penalty: 0 Presence penalty: 0
Supported regions	Model availability	Global: global Multi-region: us, eu
	ML processing	Multi-region: us, eu
	Provisioned Throughput	Global: global Multi-region: us, eu
	Standard PayGo	Global: global Multi-region: us, eu
Versions	gemini-3.6-flash Launch stage: GA Release date: July 21, 2026 Retirement date^†: November 19, 2026
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	Batch inference	Data residency CMEK VPC-SC AXT
	Context caching	Data residency CMEK VPC-SC AXT
	See Security controls for more information.

^† Listed retirement dates refer to retirement of support in Gemini Enterprise Agent Platform. Models may remain accessible through the Gemini API after these dates have passed. The Gemini API is not a Google Cloud offering and is subject to its own terms of service. For details, see the Gemini API documentation.