Gemini 2.5 Flash

Gemini 2.5 Flash is our best model in terms of price and performance, and offers well-rounded capabilities. Gemini 2.5 Flash is our first Flash model that features thinking capabilities, which lets you see the thinking process that the model goes through when generating its response.

For even more detailed technical information on Gemini 2.5 Flash (such as performance benchmarks, information on our training datasets, efforts on sustainability, intended usage and limitations, and our approach to ethics and safety), see our technical report on our Gemini 2.5 models.

2.5 Flash

Try in Agent Studio View in Model Garden

Model ID	gemini-2.5-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	65,535 (default)
Capabilities	Supported Grounding with Google Search Code execution Supervised fine-tuning Continuous tuning Preference tuning Tuning checkpoints System instructions Structured output Function calling Count Tokens Thinking Implicit context caching Explicit context caching Chat completions Not supported Gemini Live API Content Credentials (C2PA)
Consumption options	Supported Provisioned Throughput Standard PayGo with Usage Tiers Priority PayGo Batch inference Not supported Flex PayGo
	See Consumption options for more information.
Input size limit	500 MB
Technical specifications	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
	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
	Audio	Maximum audio length per prompt: Approximately 8.4 hours, or up to 1 million tokens Maximum number of audio files per prompt: 1 Speech understanding for: Audio summarization, transcription, and translation 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
	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
	Parameter defaults	Temperature: 0.0-2.0 (default 1.0) topP: 0.0-1.0 (default 0.95) topK: 64 (fixed) candidateCount: 1–8 (default 1)
Supported regions	Model availability	Global global United States us-central1 us-east1 us-east4 us-east5 us-south1 us-west1 us-west4 Canada northamerica-northeast1 South America southamerica-east1 Europe europe-central2 europe-north1 europe-southwest1 europe-west1 europe-west2 europe-west3 europe-west4 europe-west8 europe-west9 Asia Pacific asia-northeast1 asia-northeast3 asia-south1 asia-southeast1 australia-southeast1 Global global
	ML processing	United States Multi-region Canada northamerica-northeast1 South America southamerica-east1 Europe Multi-region europe-west2 europe-west3 europe-west9 Asia Pacific asia-northeast1 asia-northeast3 asia-south1 asia-southeast1 australia-southeast1
	See Deployments and endpoints for more information.
Knowledge cutoff date	January 2025
Versions	gemini-2.5-flash Launch stage: GA Release date: June 17, 2025 Discontinuation date: Not before October 16, 2026
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	Batch inference	Data residency CMEK VPC-SC AXT
	Tuning	Data residency CMEK VPC-SC AXT
	Context caching	Data residency CMEK VPC-SC AXT
	RAG Engine	Data residency CMEK VPC-SC AXT
	Grounding with Google Search and Grounding with Google Maps	Data residency CMEK VPC-SC AXT
	See Security controls for more information.
Pricing	See Pricing.

2.5 Flash

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Caution: gemini-2.5-flash-preview-09-2025 will be discontinued on July 9, 2026. Update your application to use gemini-2.5-flash or other supported model.

Try in Agent Studio Deploy example app

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

Model ID	gemini-2.5-flash-preview-09-2025
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	65,535 (default)
Capabilities	Supported Grounding with Google Search Code execution System instructions Structured output Function calling Count Tokens Thinking Implicit context caching Explicit context caching Chat completions Not supported Supervised fine-tuning Continuous tuning Preference tuning Tuning checkpoints Gemini Live API Content Credentials (C2PA)
Consumption options	Supported Provisioned Throughput Standard PayGo Not supported Flex PayGo Priority PayGo Batch inference
	See Consumption options for more information.
Technical specifications	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
	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
	Audio	Maximum audio length per prompt: Approximately 8.4 hours, or up to 1 million tokens Maximum number of audio files per prompt: 1 Speech understanding for: Audio summarization, transcription, and translation 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
	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
	Parameter defaults	Temperature: 0.0-2.0 (default 1.0) topP: 0.0-1.0 (default 0.95) topK: 64 (fixed) candidateCount: 1–8 (default 1)
Supported regions	Model availability	Global global
	See Deployments and endpoints for more information.
Knowledge cutoff date	January 2025
Versions	gemini-2.5-flash-preview-09-2025 Launch stage: Public preview Release date: September 25, 2025 Discontinuation date: July 9, 2026
Pricing	See Pricing.