Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.

Gemini 2.0 Flash

This page provides an overview of Gemini 2.0 Flash, covering the following topics:

Gemini 2.0 Flash: The core model for general-purpose multimodal tasks.
Image generation (Preview): A feature for generating images from text prompts.
Live API (Preview): A specialized API for real-time, low-latency applications.

Gemini 2.0 Flash delivers next-generation features and improved capabilities designed for the agentic era, including superior speed, built-in tool use, multimodal generation, and a 1M token context window. Gemini 2.0 Flash improves upon our previous Flash model and offers enhanced quality at similar speeds.

For even more detailed technical information on Gemini 2.0 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 the model card for Gemini 2.0 Flash.

Model / Feature	Description	Use Case
Gemini 2.0 Flash	The core multimodal model with a 1M token context window.	Ideal for general-purpose applications requiring text, image, audio, and video understanding and generation at high speed.
Image generation (Preview)	A specialized feature for creating images from text prompts.	Best for applications that need to generate high-quality images from descriptive text.
Live API (Preview)	A specialized API endpoint designed for real-time interactions.	Suitable for low-latency, streaming applications.

2.0 Flash

Try in Vertex AI View in Model Garden (Preview) Deploy example app

Note: To use the "Deploy example app" feature, you need a Google Cloud project with billing and Vertex AI API enabled.

Technical specifications
Model ID	`gemini-2.0-flash`
Supported inputs & outputs	Inputs: Text, Code, Images, Audio, Video Outputs: Text
Token limits	Maximum input tokens: 1,048,576 Maximum output tokens: 8,192 (default)
Capabilities	Supported Grounding with Google Search Code execution Tuning System instructions Structured output Batch prediction Function calling Count Tokens Context caching Vertex AI RAG Engine Chat completions Not supported Live API Preview feature Thinking
Usage types	Supported Provisioned Throughput Dynamic shared quota Not supported Fixed quota
Input size limit	500 MB
	Images	Maximum images per prompt: 3,000 Maximum image size: 7 MB Maximum tokens per minute (TPM) per project: High/Medium/Default media resolution: US/Asia: 40 M EU: 10 M Low media resolution: US/Asia: 10 M EU: 2.6 M Supported MIME types: `image/png`, `image/jpeg`, `image/webp`
	Documents	Maximum number of files per prompt: 3,000 Maximum number of pages per file: 1,000 Maximum file size per file: 50 MB Maximum tokens per minute (TPM) per project¹: US/Asia: 3.4 M EU: 3.4 M 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 Maximum tokens per minute (TPM): High/Medium/Default media resolution: US/Asia: 38 M EU: 10 M Low media resolution: US/Asia: 10 M EU: 2.5 M 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: Appropximately 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 Maximum tokens per minute (TPM): US/Asia: 3.5 M EU: 3.5 M Supported MIME types: `audio/x-aac`, `audio/flac`, `audio/mp3`, `audio/m4a`, `audio/mpeg`, `audio/mpga`, `audio/mp4`, `audio/opus`, `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 (Includes dynamic shared quota & Provisioned Throughput)	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
	ML processing	United States Multi-region Europe Multi-region
	See Data residency for more information.
Knowledge cutoff date	June 2024
Versions	`gemini-2.0-flash-001` Launch stage: Generally available Release date: February 5, 2025 Discontinuation date: February 5, 2026
Security controls
	Online prediction	Data residency (at rest) Supported Customer-managed encryption keys (CMEK) Supported VPC Service Controls Supported Access Transparency (AXT) Supported
	Batch prediction	Data residency (at rest) Supported Customer-managed encryption keys (CMEK) Not supported VPC Service Controls Supported Access Transparency (AXT) Not supported
	Tuning	Data residency (at rest) Supported Customer-managed encryption keys (CMEK) Supported VPC Service Controls Supported Access Transparency (AXT) Not supported
	See Security controls for more information.
Pricing	See Pricing.

Image generation

Try in Vertex AI

Technical specifications
Model ID	`gemini-2.0-flash-preview-image-generation`
Supported inputs & outputs	Inputs: Text, Code, Images, Audio, Video Outputs: Text and image
Token limits	Maximum input tokens: 32,768 Maximum output tokens: 8,192 (default)
Capabilities	Supported System instructions Count Tokens Not supported Grounding with Google Search Code execution Tuning Structured output Batch prediction Function calling Live API Preview feature Thinking Context caching Vertex AI RAG Engine
Usage types	Supported Dynamic shared quota Not supported Fixed quota Provisioned Throughput
Input size limit	500 MB
	Images	Maximum images per prompt: 3,000 Maximum image size: 7 MB Maximum number of output images per prompt: 10 Maximum tokens per minute (TPM) per project: High/Medium/Default media resolution: US/Asia: 40 M EU: 10 M Low media resolution: US/Asia: 10 M EU: 3 M Supported MIME types: `image/png`, `image/jpeg`, `image/webp`
	Documents	Maximum number of files per prompt: 3,000 Maximum number of pages per file: 1,000 Maximum file size per file: 50 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 Maximum tokens per minute (TPM): High/Medium/Default media resolution: US/Asia: 37.9 M EU: 9.5 M Low media resolution: US/Asia: 1 G EU: 2.5 M 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: Appropximately 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 Maximum tokens per minute (TPM): US/Asia: 1.7 M EU: 0.4 M Supported MIME types: `audio/x-aac`, `audio/flac`, `audio/mp3`, `audio/m4a`, `audio/mpeg`, `audio/mpga`, `audio/mp4`, `audio/opus`, `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
	See Data residency for more information.
Knowledge cutoff date	August 2024
Versions	`gemini-2.0-flash-preview-image-generation` Launch stage: Public preview Release date: May 6, 2025
Security controls
	Online prediction	Data residency (at rest) Not supported Customer-managed encryption keys (CMEK) Not supported VPC Service Controls Supported Access Transparency (AXT) Supported
	See Security controls for more information.
Pricing	See Pricing.

Live API

Try in Vertex AI

Technical specifications
Model ID	`gemini-2.0-flash-live-preview-04-09`
Supported inputs & outputs	Inputs: Audio, Video Outputs: Audio
Token limits	Maximum input tokens: 32,768 Maximum output tokens: 8,192 (default)
Capabilities	Supported Grounding with Google Search Code execution System instructions Function calling Live API Preview feature Not supported Tuning Structured output Batch prediction Thinking Context caching Vertex AI RAG Engine
Usage types	Supported Dynamic shared quota Not supported Fixed quota Provisioned Throughput
Input size limit	500 MB
	Video	Maximum video length (with audio): Approximately 45 minutes Maximum video length (without audio): Approximately 1 hour Maximum number of videos per prompt: 10 Maximum tokens per minute (TPM): High/Medium/Default media resolution: US/Asia: 37.9 M EU: 9.5 M Low media resolution: US/Asia: 1 G EU: 2.5 M 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: Appropximately 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 Maximum tokens per minute (TPM): US/Asia: 1.7 M EU: 0.4 M Supported MIME types: `audio/x-aac`, `audio/flac`, `audio/mp3`, `audio/m4a`, `audio/mpeg`, `audio/mpga`, `audio/mp4`, `audio/opus`, `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	United States us-central1
	See Data residency for more information.
Knowledge cutoff date	June 2024
Versions	`gemini-2.0-flash-live-preview-04-09` Launch stage: Public preview Release date: April 9, 2025
Security controls
	Online prediction	Data residency (at rest) Not supported Customer-managed encryption keys (CMEK) Not supported VPC Service Controls Supported Access Transparency (AXT) Supported
	See Security controls for more information.
Pricing	See Pricing.

Gemini 2.0 Flash Stay organized with collections Save and categorize content based on your preferences.

2.0 Flash

Image generation

Live API

Gemini 2.0 Flash