Gemini 2.5 Flash-Lite

Important: This model is being retired on October 20th, 2026. See Migrate to latest Gemini models for recommended replacement models.

Gemini 2.5 Flash-Lite is our most balanced Gemini model, optimized for low latency use cases. It comes with the same capabilities that make other Gemini 2.5 models helpful, such as the ability to turn thinking on at different budgets, connecting to tools like Grounding with Google Search and code execution, multimodal input, and a 1 million-token context length.

Try in Agent Studio Deploy example app Pricing

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

Model ID	gemini-2.5-flash-lite
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 Supervised fine-tuning, continuous tuning, preference tuning, tuning checkpoints Supported Agentic video understanding Not supported
Tools	Grounding Google Search, Parallel Web Search, Exa Web Search Supported Code execution Supported Function calling Supported URL context Supported Computer use Not supported
APIs	GenerateContent API Supported Interactions API Not supported Gemini Live API Not supported Count Tokens API Supported Chat Completions API Not supported
Consumption options	Provisioned Throughput Supported Batch inference Supported Pay-as-you-go Standard PayGo with Usage Tiers, Priority PayGo Supported Fixed quota Not supported
Input size limit	500 MiB compressed
Technical specifications	Image	Maximum images per prompt: 3,000 (images and PDFs combined; up to 10 HTTP or HTTPS URLs on non-migrated regional, tuned, or Model Armor endpoints) Maximum inline part size: 256 MB (30 MiB on non-migrated endpoints) Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB (30 MiB on non-migrated endpoints) Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB Maximum file size per file for direct local uploads in the console: 7 MiB inline (up to 50 MiB staged to Cloud Storage) Maximum file size per file for Google Drive imports in the console: 7 MB (10 MB total) Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Text	Maximum number of files per prompt: 3,000 PDFs (shared with images; up to 6,500 total files when including plain text) Maximum number of pages per file: 1,000 Maximum inline part size: 256 MB (50 MiB for PDF or 7 MiB for plain text on non-migrated endpoints) Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB (50 MiB for PDF or 7 MiB for plain text on non-migrated endpoints) Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB (7 MiB for plain text on non-migrated endpoints) Maximum file size per file for direct local uploads in the console: 7 MiB inline (up to 50 MiB staged to Cloud Storage) Maximum file size per file for Google Drive imports in the console: 7 MB (10 MB total) 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 (up to 1 HTTP or HTTPS URL on non-migrated endpoints) Maximum inline part size: 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB 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: 1,000 (up to 1 HTTP or HTTPS URL on non-migrated endpoints) Maximum inline part size: 256 MB Maximum file size per file from Cloud Storage: 2 GiB minus 500 KiB Maximum file size per file from public HTTP or HTTPS URLs: 15 MiB 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
	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 Europe: europe-central2, europe-north1, europe-southwest1, europe-west1, europe-west4, europe-west8, europe-west9
Versions	gemini-2.5-flash-lite Launch stage: GA Release date: July 22, 2025 Retirement date^†: October 20, 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.

^† 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.