OUR MOST INTELLIGENT MODEL
Gemini 3 Pro
The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art reasoning.
Expand to learn more
Try in Google AI Studio
Model details
Gemini 3 Pro Preview
| Property |
Description |
| id_cardModel code |
gemini-3-pro-preview |
| saveSupported data types |
Inputs Text, Image, Video, Audio, and PDF Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-3-pro-preview |
| calendar_monthLatest update |
November 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 3 Pro Image Preview
| Property |
Description |
| id_cardModel code |
gemini-3-pro-image-preview |
| saveSupported data types |
Inputs Image and Text Output Image and Text |
| token_autoToken limits^[*]^ |
Input token limit 65,536 Output token limit 32,768 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Not supported Code execution Not supported File search Not supported Function calling Not supported Grounding with Google Maps Not supported Image generation Supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-3-pro-image-preview |
| calendar_monthLatest update |
November 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
OUR MOST BALANCED MODEL, DESIGNED TO SCALE
Gemini 3 Flash
Our most balanced model built for speed, scale, and frontier intelligence.
Expand to learn more
Try in Google AI Studio
Model details
Gemini 3 Flash Preview
| Property |
Description |
| id_cardModel code |
gemini-3-flash-preview |
| saveSupported data types |
Inputs Text, Image, Video, Audio, and PDF Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-3-flash-preview |
| calendar_monthLatest update |
December 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
FAST AND INTELLIGENT
Gemini 2.5 Flash
Our best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.
Expand to learn more
Try in Google AI Studio
Model details
Gemini 2.5 Flash
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash |
| saveSupported data types |
Inputs Text, images, video, audio Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Stable: gemini-2.5-flash |
| calendar_monthLatest update |
June 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 2.5 Flash Preview
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-preview-09-2025 |
| saveSupported data types |
Inputs Text, images, video, audio Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL Context Supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-2.5-flash-preview-09-2025 |
| calendar_monthLatest update |
September 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 2.5 Flash Image
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-image |
| saveSupported data types |
Inputs Images and text Output Images and text |
| token_autoToken limits^[*]^ |
Input token limit 65,536 Output token limit 32,768 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Not Supported File search Not Supported Function calling Not supported Grounding with Google Maps Not supported Image generation Supported Live API Not Supported Search grounding Not Supported Structured outputs Supported Thinking Not Supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Stable: gemini-2.5-flash-image - Deprecated: gemini-2.5-flash-image-preview |
| calendar_monthLatest update |
October 2025 |
| cognition_2Knowledge cutoff |
June 2025 |
Gemini 2.5 Flash Live
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-native-audio-preview-12-2025 |
| saveSupported data types |
Inputs Audio, video, text Output Audio and text |
| token_autoToken limits^[*]^ |
Input token limit 131,072 Output token limit 8,192 |
| handymanCapabilities |
Audio generation Supported Batch API Not supported Caching Not supported Code execution Not supported File search Not Supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Supported Search grounding Supported Structured outputs Not supported Thinking Supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-2.5-flash-native-audio-preview-12-2025 - Preview: gemini-2.5-flash-native-audio-preview-09-2025 |
| calendar_monthLatest update |
September 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 2.5 Flash TTS
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-preview-tts |
| saveSupported data types |
Inputs Text Output Audio |
| token_autoToken limits^[*]^ |
Input token limit 8,192 Output token limit 16,384 |
| handymanCapabilities |
Audio generation Supported Batch API Supported Caching Not supported Code execution Not supported File search Not Supported Function calling Not supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Not supported Structured outputs Not supported Thinking Not supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - gemini-2.5-flash-preview-tts |
| calendar_monthLatest update |
December 2025 |
ULTRA FAST
Gemini 2.5 Flash-Lite
Our fastest flash model optimized for cost-efficiency and high throughput.
Expand to learn more
Try in Google AI Studio
Model details
Gemini 2.5 Flash-Lite
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-lite |
| saveSupported data types |
Inputs Text, image, video, audio, PDF Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Stable: gemini-2.5-flash-lite |
| calendar_monthLatest update |
July 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 2.5 Flash-Lite Preview
| Property |
Description |
| id_cardModel code |
gemini-2.5-flash-lite-preview-09-2025 |
| saveSupported data types |
Inputs Text, image, video, audio, PDF Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-2.5-flash-lite-preview-09-2025 |
| calendar_monthLatest update |
September 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
OUR ADVANCED THINKING MODEL
Gemini 2.5 Pro
Our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.
Expand to learn more
Try in Google AI Studio
Model details
Gemini 2.5 Pro
| Property |
Description |
| id_cardModel code |
gemini-2.5-pro |
| saveSupported data types |
Inputs Audio, images, video, text, and PDF Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 65,536 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| 123Versions |
Read the model version patterns for more details. - Stable: gemini-2.5-pro |
| calendar_monthLatest update |
June 2025 |
| cognition_2Knowledge cutoff |
January 2025 |
Gemini 2.5 Pro TTS
| Property |
Description |
| id_cardModel code |
gemini-2.5-pro-preview-tts |
| saveSupported data types |
Inputs Text Output Audio |
| token_autoToken limits^[*]^ |
Input token limit 8,192 Output token limit 16,384 |
| handymanCapabilities |
Audio generation Supported Batch API Supported Caching Not supported Code execution Not supported File search Not Supported Function calling Not supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Not supported Structured outputs Not supported Thinking Not supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - gemini-2.5-pro-preview-tts |
| calendar_monthLatest update |
December 2025 |
Previous Gemini models
OUR SECOND GENERATION WORKHORSE MODEL
Gemini 2.0 Flash
Our second generation workhorse model, with a 1 million token context window.
Expand to learn more
Gemini 2.0 Flash delivers next-gen features and improved capabilities,
including superior speed, native tool use, and a 1M token
context window.
Try in Google AI Studio
Model details
Gemini 2.0 Flash
| Property |
Description |
| id_cardModel code |
gemini-2.0-flash |
| saveSupported data types |
Inputs Audio, images, video, and text Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 8,192 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported File search Not supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Experimental URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Latest: gemini-2.0-flash - Stable: gemini-2.0-flash-001 - Experimental: gemini-2.0-flash-exp |
| calendar_monthLatest update |
February 2025 |
| cognition_2Knowledge cutoff |
August 2024 |
Gemini 2.0 Flash Image
| Property |
Description |
| id_cardModel code |
gemini-2.0-flash-preview-image-generation |
| saveSupported data types |
Inputs Audio, images, video, and text Output Text and images |
| token_autoToken limits^[*]^ |
Input token limit 32,768 Output token limit 8,192 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Not Supported File search Not supported Function calling Not supported Grounding with Google Maps Not supported Image generation Supported Live API Not Supported Search grounding Not Supported Structured outputs Supported Thinking Not Supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Preview: gemini-2.0-flash-preview-image-generation - gemini-2.0-flash-preview-image-generation is not currently supported in a number of countries in Europe, Middle East & Africa |
| calendar_monthLatest update |
May 2025 |
| cognition_2Knowledge cutoff |
August 2024 |
OUR SECOND GENERATION FAST MODEL
Gemini 2.0 Flash-Lite
Our second generation small workhorse model, with a 1 million token context window.
Expand to learn more
A Gemini 2.0 Flash model optimized for cost efficiency and low latency.
Try in Google AI Studio
Model details
| Property |
Description |
| id_cardModel code |
gemini-2.0-flash-lite |
| saveSupported data types |
Inputs Audio, images, video, and text Output Text |
| token_autoToken limits^[*]^ |
Input token limit 1,048,576 Output token limit 8,192 |
| handymanCapabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Not supported File search Not supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Not supported Search grounding Not supported Structured outputs Supported Thinking Not Supported URL context Not supported |
| 123Versions |
Read the model version patterns for more details. - Latest: gemini-2.0-flash-lite - Stable: gemini-2.0-flash-lite-001 |
| calendar_monthLatest update |
February 2025 |
| cognition_2Knowledge cutoff |
August 2024 |
Model version name patterns
Gemini models are available in either stable , preview , latest , or
experimental versions.
| Note: The following list refers to the model string naming convention as of September, 2025. Models released prior to that may have different naming conventions. Refer to the exact model string if you are using an older model.
Stable
Points to a specific stable model. Stable models usually don't change. Most
production apps should use a specific stable model.
For example: gemini-2.5-flash.
Preview
Points to a preview model which may be used for production. Preview models will
typically have billing enabled, might come with more restrictive rate limits and
will be deprecated with at least 2 weeks notice.
For example: gemini-2.5-flash-preview-09-2025.
Latest
Points to the latest release for a specific model variation. This can be a
stable, preview or experimental release. This alias will get hot-swapped with
every new release of a specific model variation. A 2-week notice will
be provided through email before the version behind latest is changed.
For example: gemini-flash-latest.
Experimental
Points to an experimental model which will typically be not be suitable for
production use and come with more restrictive rate limits. We release
experimental models to gather feedback and get our latest updates into the hands
of developers quickly.
Experimental models are not stable and availability of model endpoints is
subject to change.
Model deprecations
For information about model deprecations, visit the Gemini deprecations page.
1---2name: gemini-3-pro3description: The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art…4---5<br />67OUR MOST INTELLIGENT MODEL89## Gemini 3 Pro101112The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art reasoning.1314### Expand to learn more1516[Try in Google AI Studio](https://aistudio.google.com?model=gemini-3-pro-preview)1718#### Model details1920### Gemini 3 Pro Preview2122| Property | Description |23|---|---|24| id_cardModel code | `gemini-3-pro-preview` |25| saveSupported data types | **Inputs** Text, Image, Video, Audio, and PDF **Output** Text |26| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |27| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |28| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `Preview: gemini-3-pro-preview` |29| calendar_monthLatest update | November 2025 |30| cognition_2Knowledge cutoff | January 2025 |3132### Gemini 3 Pro Image Preview3334| Property | Description |35|---|---|36| id_cardModel code | `gemini-3-pro-image-preview` |37| saveSupported data types | **Inputs** Image and Text **Output** Image and Text |38| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 65,536 **Output token limit** 32,768 |39| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Not supported **Code execution** Not supported **File search** Not supported **Function calling** Not supported **Grounding with Google Maps** Not supported **Image generation** Supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Not supported |40| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `Preview: gemini-3-pro-image-preview` |41| calendar_monthLatest update | November 2025 |42| cognition_2Knowledge cutoff | January 2025 |4344OUR MOST BALANCED MODEL, DESIGNED TO SCALE4546## Gemini 3 Flash474849Our most balanced model built for speed, scale, and frontier intelligence.5051### Expand to learn more5253[Try in Google AI Studio](https://aistudio.google.com?model=gemini-3-flash-preview)5455#### Model details5657### Gemini 3 Flash Preview5859| Property | Description |60|---|---|61| id_cardModel code | `gemini-3-flash-preview` |62| saveSupported data types | **Inputs** Text, Image, Video, Audio, and PDF **Output** Text |63| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |64| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |65| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `Preview: gemini-3-flash-preview` |66| calendar_monthLatest update | December 2025 |67| cognition_2Knowledge cutoff | January 2025 |6869FAST AND INTELLIGENT7071## Gemini 2.5 Flash727374Our best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.7576### Expand to learn more7778[Try in Google AI Studio](https://aistudio.google.com?model=gemini-2.5-flash)7980#### Model details8182### Gemini 2.5 Flash8384| Property | Description |85|---|---|86| id_cardModel code | `gemini-2.5-flash` |87| saveSupported data types | **Inputs** Text, images, video, audio **Output** Text |88| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |89| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |90| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Stable: `gemini-2.5-flash` |91| calendar_monthLatest update | June 2025 |92| cognition_2Knowledge cutoff | January 2025 |9394### Gemini 2.5 Flash Preview9596| Property | Description |97|---|---|98| id_cardModel code | `gemini-2.5-flash-preview-09-2025` |99| saveSupported data types | **Inputs** Text, images, video, audio **Output** Text |100| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |101| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL Context** Supported |102| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Preview: `gemini-2.5-flash-preview-09-2025` |103| calendar_monthLatest update | September 2025 |104| cognition_2Knowledge cutoff | January 2025 |105106### Gemini 2.5 Flash Image107108| Property | Description |109|---|---|110| id_cardModel code | `gemini-2.5-flash-image` |111| saveSupported data types | **Inputs** Images and text **Output** Images and text |112| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 65,536 **Output token limit** 32,768 |113| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Not Supported **File search** Not Supported **Function calling** Not supported **Grounding with Google Maps** Not supported **Image generation** Supported **Live API** Not Supported **Search grounding** Not Supported **Structured outputs** Supported **Thinking** Not Supported **URL context** Not supported |114| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Stable: `gemini-2.5-flash-image` - Deprecated: `gemini-2.5-flash-image-preview` |115| calendar_monthLatest update | October 2025 |116| cognition_2Knowledge cutoff | June 2025 |117118### Gemini 2.5 Flash Live119120| Property | Description |121|---|---|122| id_cardModel code | `gemini-2.5-flash-native-audio-preview-12-2025` |123| saveSupported data types | **Inputs** Audio, video, text **Output** Audio and text |124| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 131,072 **Output token limit** 8,192 |125| handymanCapabilities | **Audio generation** Supported **Batch API** Not supported **Caching** Not supported **Code execution** Not supported **File search** Not Supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Supported **Search grounding** Supported **Structured outputs** Not supported **Thinking** Supported **URL context** Not supported |126| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Preview: `gemini-2.5-flash-native-audio-preview-12-2025` - Preview: `gemini-2.5-flash-native-audio-preview-09-2025` |127| calendar_monthLatest update | September 2025 |128| cognition_2Knowledge cutoff | January 2025 |129130### Gemini 2.5 Flash TTS131132| Property | Description |133|---|---|134| id_cardModel code | `gemini-2.5-flash-preview-tts` |135| saveSupported data types | **Inputs** Text **Output** Audio |136| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 8,192 **Output token limit** 16,384 |137| handymanCapabilities | **Audio generation** Supported **Batch API** Supported **Caching** Not supported **Code execution** Not supported **File search** Not Supported **Function calling** Not supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Not supported **Structured outputs** Not supported **Thinking** Not supported **URL context** Not supported |138| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `gemini-2.5-flash-preview-tts` |139| calendar_monthLatest update | December 2025 |140141ULTRA FAST142143## Gemini 2.5 Flash-Lite144145146Our fastest flash model optimized for cost-efficiency and high throughput.147148### Expand to learn more149150[Try in Google AI Studio](https://aistudio.google.com?model=gemini-2.5-flash-lite)151152#### Model details153154### Gemini 2.5 Flash-Lite155156| Property | Description |157|---|---|158| id_cardModel code | `gemini-2.5-flash-lite` |159| saveSupported data types | **Inputs** Text, image, video, audio, PDF **Output** Text |160| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |161| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |162| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Stable: `gemini-2.5-flash-lite` |163| calendar_monthLatest update | July 2025 |164| cognition_2Knowledge cutoff | January 2025 |165166### Gemini 2.5 Flash-Lite Preview167168| Property | Description |169|---|---|170| id_cardModel code | `gemini-2.5-flash-lite-preview-09-2025` |171| saveSupported data types | **Inputs** Text, image, video, audio, PDF **Output** Text |172| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |173| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |174| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Preview: `gemini-2.5-flash-lite-preview-09-2025` |175| calendar_monthLatest update | September 2025 |176| cognition_2Knowledge cutoff | January 2025 |177178OUR ADVANCED THINKING MODEL179180## Gemini 2.5 Pro181182183Our state-of-the-art thinking model, capable of reasoning over complex problems in code, math, and STEM, as well as analyzing large datasets, codebases, and documents using long context.184185### Expand to learn more186187[Try in Google AI Studio](https://aistudio.google.com?model=gemini-2.5-pro)188189#### Model details190191### Gemini 2.5 Pro192193| Property | Description |194|---|---|195| id_cardModel code | `gemini-2.5-pro` |196| saveSupported data types | **Inputs** Audio, images, video, text, and PDF **Output** Text |197| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 65,536 |198| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Supported **Function calling** Supported **Grounding with Google Maps** Supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Supported **URL context** Supported |199| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `Stable: gemini-2.5-pro` |200| calendar_monthLatest update | June 2025 |201| cognition_2Knowledge cutoff | January 2025 |202203### Gemini 2.5 Pro TTS204205| Property | Description |206|---|---|207| id_cardModel code | `gemini-2.5-pro-preview-tts` |208| saveSupported data types | **Inputs** Text **Output** Audio |209| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 8,192 **Output token limit** 16,384 |210| handymanCapabilities | **Audio generation** Supported **Batch API** Supported **Caching** Not supported **Code execution** Not supported **File search** Not Supported **Function calling** Not supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Not supported **Structured outputs** Not supported **Thinking** Not supported **URL context** Not supported |211| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - `gemini-2.5-pro-preview-tts` |212| calendar_monthLatest update | December 2025 |213214<br />215216## Previous Gemini models217218OUR SECOND GENERATION WORKHORSE MODEL219220## Gemini 2.0 Flash221222223Our second generation workhorse model, with a 1 million token context window.224225### Expand to learn more226227228Gemini 2.0 Flash delivers next-gen features and improved capabilities,229including superior speed, native tool use, and a 1M token230context window.231232[Try in Google AI Studio](https://aistudio.google.com?model=gemini-2.0-flash)233234#### Model details235236### Gemini 2.0 Flash237238| Property | Description |239|---|---|240| id_cardModel code | `gemini-2.0-flash` |241| saveSupported data types | **Inputs** Audio, images, video, and text **Output** Text |242| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 8,192 |243| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Supported **File search** Not supported **Function calling** Supported **Grounding with Google Maps** Supported **Image generation** Not supported **Live API** Not supported **Search grounding** Supported **Structured outputs** Supported **Thinking** Experimental **URL context** Not supported |244| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Latest: `gemini-2.0-flash` - Stable: `gemini-2.0-flash-001` - Experimental: `gemini-2.0-flash-exp` |245| calendar_monthLatest update | February 2025 |246| cognition_2Knowledge cutoff | August 2024 |247248### Gemini 2.0 Flash Image249250| Property | Description |251|---|---|252| id_cardModel code | `gemini-2.0-flash-preview-image-generation` |253| saveSupported data types | **Inputs** Audio, images, video, and text **Output** Text and images |254| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 32,768 **Output token limit** 8,192 |255| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Not Supported **File search** Not supported **Function calling** Not supported **Grounding with Google Maps** Not supported **Image generation** Supported **Live API** Not Supported **Search grounding** Not Supported **Structured outputs** Supported **Thinking** Not Supported **URL context** Not supported |256| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Preview: `gemini-2.0-flash-preview-image-generation` - gemini-2.0-flash-preview-image-generation is not currently supported in a number of countries in Europe, Middle East \& Africa |257| calendar_monthLatest update | May 2025 |258| cognition_2Knowledge cutoff | August 2024 |259260OUR SECOND GENERATION FAST MODEL261262## Gemini 2.0 Flash-Lite263264265Our second generation small workhorse model, with a 1 million token context window.266267### Expand to learn more268269A Gemini 2.0 Flash model optimized for cost efficiency and low latency.270271[Try in Google AI Studio](https://aistudio.google.com?model=gemini-2.0-flash-lite)272273#### Model details274275| Property | Description |276|---|---|277| id_cardModel code | `gemini-2.0-flash-lite` |278| saveSupported data types | **Inputs** Audio, images, video, and text **Output** Text |279| token_autoToken limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 1,048,576 **Output token limit** 8,192 |280| handymanCapabilities | **Audio generation** Not supported **Batch API** Supported **Caching** Supported **Code execution** Not supported **File search** Not supported **Function calling** Supported **Grounding with Google Maps** Not supported **Image generation** Not supported **Live API** Not supported **Search grounding** Not supported **Structured outputs** Supported **Thinking** Not Supported **URL context** Not supported |281| 123Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Latest: `gemini-2.0-flash-lite` - Stable: `gemini-2.0-flash-lite-001` |282| calendar_monthLatest update | February 2025 |283| cognition_2Knowledge cutoff | August 2024 |284285<br />286287## Model version name patterns288289Gemini models are available in either *stable* , *preview* , *latest* , or290*experimental* versions.291| **Note:** The following list refers to the model string naming convention as of September, 2025. Models released prior to that may have different naming conventions. Refer to the exact model string if you are using an older model.292293### Stable294295Points to a specific stable model. Stable models usually don't change. Most296production apps should use a specific stable model.297298For example: `gemini-2.5-flash`.299300### Preview301302Points to a preview model which may be used for production. Preview models will303typically have billing enabled, might come with more restrictive rate limits and304will be deprecated with at least 2 weeks notice.305306For example: `gemini-2.5-flash-preview-09-2025`.307308### Latest309310Points to the latest release for a specific model variation. This can be a311stable, preview or experimental release. This alias will get hot-swapped with312every new release of a specific model variation. A **2-week notice** will313be provided through email before the version behind latest is changed.314315For example: `gemini-flash-latest`.316317### Experimental318319Points to an experimental model which will typically be not be suitable for320production use and come with more restrictive rate limits. We release321experimental models to gather feedback and get our latest updates into the hands322of developers quickly.323324Experimental models are not stable and availability of model endpoints is325subject to change.326327## Model deprecations328329For information about model deprecations, visit the [Gemini deprecations](https://ai.google.dev/gemini-api/docs/deprecations) page.
tools-only