Google models

Featured Gemini models

2.5 Pro

A preview version of our most advanced reasoning model to date

  • Input audio, images, video, and text, get text responses
  • See the model's thinking process as part of the response
  • Best for solving complex coding and reasoning problems

2.0 Flash

Our newest multimodal model, with next generation features and improved capabilities

  • Input audio, images, video, and text, get text responses
  • Generate code and images, extract data, analyze files, generate graphs, and more
  • Low latency, enhanced performance, built to power agentic experiences

2.0 Flash-Lite

A Gemini 2.0 Flash model optimized for cost efficiency and low latency

  • Input audio, images, video, and text, get text responses
  • Outperforms 1.5 Flash on the majority of benchmarks
  • A 1 million token context window and multimodal input, like Flash 2.0

Generally available Gemini models

sparkGemini 2.0 FlashOur newest multimodal model, with next generation features and improved capabilities
performance_autoGemini 2.0 Flash-LiteA Gemini 2.0 Flash model optimized for cost efficiency and low latency

Preview Gemini models

previewGemini 2.5 ProOur most advanced reasoning model to date
previewGemini 2.5 FlashGemini 2.5 Flash is a thinking model that offers great, well-rounded capabilities. It is designed to offer a balance between price and performance.

Gemma models

Gemma 3Our latest Gemma open model, featuring the ability to solve a wide variety of tasks with text and image input, support for over 140 languages, and long 128K context window
Gemma 2The second of generation of our open models featuring text generation, summarization, and extraction
GemmaA small-sized, lightweight open model supporting text generation, summarization, and extraction
ShieldGemma 2Instruction tuned models for evaluating the safety of text and images against a set of defined safety policies
PaliGemmaOur open vision-language model that combines SigLIP and Gemma
CodeGemmaPowerful, lightweight open model that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following
TxGemmaGenerates predictions, classifications or text based on therapeutic related data and can be used to efficiently build AI models for therapeutic-related tasks with less data and less compute

Embeddings models

width_normalEmbeddings for TextConverts text data into vector representations for semantic search, classification, clustering, and similar tasks
width_normalMultimodal EmbeddingsGenerates vectors based on images, which can be used for downstream tasks like image classification, image search, and more

Imagen models

photo_sparkImagen 3 for GenerationUse text prompts to generate novel images
image_edit_autoImagen 3 for Editing and CustomizationUse text prompts to edit existing input images, or parts of an image with a mask or generate new images based upon the context provided by input reference images
visual_effectsImagen 2 for Generation and EditingUse text prompts to generative novel images, edit existing ones, edit parts of an image with a mask and more
subtitlesImagen for Captioning & VQAUse text prompts to generative novel images, edit existing ones, edit parts of an image with a mask and more

MedLM models

medical_informationMedLM-mediumHIPAA-compliant suite of medically tuned models designed to help healthcare practitioners with medical question and answer tasks, and summarization tasks for healthcare and medical documents
clinical_notesMedLM-large-largeHIPAA-compliant suite of medically tuned models designed to help healthcare practitioners with medical question and answer tasks, and summarization tasks for healthcare and medical documents

Language support

Gemini

All the Gemini models can understand and respond in the following languages:

Arabic (ar), Bengali (bn), Bulgarian (bg), Chinese (Simplified and Traditional) (zh), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Finnish (fi), French (fr), German (de), Greek (el), Hebrew (iw), Hindi (hi), Hungarian (hu), Indonesian (id), Italian (it), Japanese (ja), Korean (ko), Latvian (lv), Lithuanian (lt), Norwegian (no), Polish (pl), Portuguese (pt), Romanian (ro), Russian (ru), Serbian (sr), Slovak (sk), Slovenian (sl), Spanish (es), Swahili (sw), Swedish (sv), Thai (th), Turkish (tr), Ukrainian (uk), Vietnamese (vi)

Gemini 2.0 Flash, Gemini 1.5 Pro and Gemini 1.5 Flash models can understand and respond in the following additional languages:

Afrikaans (af), Amharic (am), Assamese (as), Azerbaijani (az), Belarusian (be), Bosnian (bs), Catalan (ca), Cebuano (ceb), Corsican (co), Welsh (cy), Dhivehi (dv), Esperanto (eo), Basque (eu), Persian (fa), Filipino (Tagalog) (fil), Frisian (fy), Irish (ga), Scots Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hawaiian (haw), Hmong (hmn), Haitian Creole (ht), Armenian (hy), Igbo (ig), Icelandic (is), Javanese (jv), Georgian (ka), Kazakh (kk), Khmer (km), Kannada (kn), Krio (kri), Kurdish (ku), Kyrgyz (ky), Latin (la), Luxembourgish (lb), Lao (lo), Malagasy (mg), Maori (mi), Macedonian (mk), Malayalam (ml), Mongolian (mn), Meiteilon (Manipuri) (mni-Mtei), Marathi (mr), Malay (ms), Maltese (mt), Myanmar (Burmese) (my), Nepali (ne), Nyanja (Chichewa) (ny), Odia (Oriya) (or), Punjabi (pa), Pashto (ps), Sindhi (sd), Sinhala (Sinhalese) (si), Samoan (sm), Shona (sn), Somali (so), Albanian (sq), Sesotho (st), Sundanese (su), Tamil (ta), Telugu (te), Tajik (tg), Uyghur (ug), Urdu (ur), Uzbek (uz), Xhosa (xh), Yiddish (yi), Yoruba (yo), Zulu (zu)

Gemma

Gemma supports only the English language.

Embeddings

Multilingual text embedding models support the following languages:

Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Sotho, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, West Frisian, Xhosa, Yiddish, Yoruba, Zulu.

Imagen 3

Imagen 3 supports the following languages:

English, Chinese, Hindi, Japanese, Korean, Portuguese, and Spanish.

MedLM

The MedLM model supports the English language.

Explore all models in Model Garden

Model Garden is a platform that helps you discover, test, customize, and deploy Google proprietary and select OSS models and assets. To explore the generative AI models and APIs that are available on Vertex AI, go to Model Garden in the Google Cloud console.

Go to Model Garden

To learn more about Model Garden, including available models and capabilities, see Explore AI models in Model Garden.

Model versions

To see all model versions, including legacy and retired models, see Model versions and lifecycle.

What's next