Google models

Featured Gemini models

4 Argon

Google's frontier model that excels at deep work in complex, real-world tasks

• Excels across coding, finance, legal, cybersecurity, and science
• Deep multi-step reasoning with configurable thinking levels
• Long-output generation up to 1 million tokens

3.8 Flash

Built for long-horizon coding and autonomous agents

• Improved response quality
• More reliable code generation
• Stronger multimodal reasoning

Nano Banana 2.1

Turn ideas into production-ready assets

• Generate high-quality images
• Capable of turn-based conversational editing
• Capable of multi-image fusion and character consistency for advanced creative workflows

Generally available Gemini models

spark Gemini 4 Argon Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.

spark Gemini 4 Argon Cyber Permissive (Gemini Frontier Cyber Model) A version of Gemini 4 Argon for defensive cybersecurity use cases. Available behind an allowlist.

spark Gemini 3.8 Flash Cyber (Gemini Cyber) Our model optimized for cyber security.

audio_spark Gemini 3.8 Live Optimized for live interactions, with improved voice quality, reliability, and real-time agent orchestration.

spark Gemini 3.8 Flash Our most intelligent workhorse model yet, built for long-horizon coding and autonomous agents.

spark Gemini 3.7 Flash Our intelligent everyday driver for developers, delivering a step forward in software engineering and feeling distinctly better to build with.

spark Gemini 3.6 Flash Optimized for complex, multi-step workflows, improved code generation, and improved multimodal reasoning—all while using fewer tokens.

performance_auto Gemini 3.5 Flash-Lite Create lightweight agentic workflows at top speeds and minimal cost.

banana_spark Gemini Nano Banana 2.1 High-fidelity, multimodal image generation and editing. Delivers significantly improved prompt adherence, text rendering, and visual quality.

banana_spark Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite) Turn ideas into production-ready assets. Designed for high-volume and latency-sensitive workloads.

banana_spark Gemini 3.1 Flash Image Turn ideas into production-ready assets. Features conversational editing, multi-image fusion, and character consistency for advanced creative workflows.

banana_spark Gemini 3 Pro Image High-fidelity image generation with reasoning-enhanced composition. Supports legible text rendering, complex multi-turn editing, and character consistency using up to 14 reference inputs.

spark Gemini 3.5 Flash Gemini 3.5 Flash delivers near-Pro intelligence at Flash-tier cost and speed: Pro-level coding proficiency, parallel agentic execution, all at the same price point as a Flash model.

performance_auto Gemini 3.1 Flash-Lite Our most cost-efficient model, optimized for low latency use cases for high-volume, cost-sensitive LLM traffic.

diamond Gemini 2.5 Pro Our high-capability model for complex reasoning and coding. Features adaptive thinking capabilities to solve complex agentic and multimodal challenges with a 1 million token context.

spark Gemini 2.5 Flash Lightning-fast and highly capable. Delivers a balance of intelligence and latency with controllable thinking budgets for versatile applications.

banana_spark Gemini 2.5 Flash Image Turn ideas into production-ready assets. Features conversational editing, multi-image fusion, and character consistency for advanced creative workflows.

performance_auto Gemini 2.5 Flash-Lite Built for massive scale. Balances cost and performance for high-throughput tasks, optimized for efficiency without sacrificing multimodal understanding.

audio_spark Gemini 2.5 Flash with Gemini Live API Designed for real-time, bidirectional streaming. Features low-latency built-in audio and affective dialogue capabilities for natural, conversational interactions.

Preview Gemini models

preview Gemini 3.8 Flash TTS Our flagship text-to-speech model for studio-grade voice fidelity, expressive acting, regional accents, and stable long-form multi-speaker audio.

preview Gemini 3.8 Flash-Lite TTS Fast, cost-efficient text-to-speech for high-throughput production workloads and voice agents.

preview Gemini Omni 1.1 Flash Generate video from text or reference assets, or edit existing videos.

preview Gemini Omni Flash Generate video from text or reference assets, or edit existing videos.

preview Gemini 3.1 Pro Our reasoning-first model optimized for complex agentic workflows and coding. Features adaptive thinking, a 1 million token context window, and integrated grounding for multimodal problem-solving.

preview Gemini 3 Flash Our best model for complex multimodal understanding, designed to tackle the most challenging agentic problems with strong coding and state-of-the-art reasoning capabilities.

Gemma models

Gemma 4 An open model well-suited for tasks like text generation, coding, and reasoning, and supporting multimodal input (text and image for all variants, and additionally audio for the E2B and E4B variants).

Gemma 3n An open model designed for efficient execution on low-resource devices, supporting multimodal input (text, image, video, and audio) and text output in over 140 languages.

Gemma 3 An open model featuring text and image input, support for over 140 languages, and a 128K context window.

Gemma 2 An open model supporting text generation, summarization, and extraction.

Gemma A small, lightweight open model supporting text generation, summarization, and extraction.

ShieldGemma 2 Instruction-tuned models for evaluating text and image safety against defined policies.

PaliGemma An open vision-language model combining SigLIP and Gemma.

CodeGemma A powerful, lightweight open model for coding tasks, including code completion, generation, and understanding.

TxGemma A model that generates predictions, classifications, or text based on therapeutic-related data, for building AI models with less data and compute.

MedGemma A collection of Gemma 3 variants trained for performance on medical text and image comprehension.

MedSigLIP A SigLIP variant trained to encode medical images and text into a common embedding space.

T5Gemma A family of lightweight encoder-decoder research models.

Embeddings models

width_normal Embeddings for Text Converts text data into vector representations for semantic search, classification, and clustering.

width_normal Multimodal Embeddings Generates vectors based on images, for tasks such as image classification and search.

Veo models

movie Veo 3 Generate Generates videos from text prompts and images with high quality.

movie Veo 3 Fast Generates videos from text prompts and images with high quality and low latency.

movie Veo 3.1 Generate Generates videos from text prompts and images with high quality.

movie Veo 3.1 Fast Generates videos from text prompts and images with high quality and low latency.

Preview Veo models

movie Veo 3.1 Lite preview Generates videos from text prompts and images with high quality and low cost.

Lyria models

music_note_spark Lyria 3 Pro (Preview) Generates full-length music tracks from text and image prompts.

music_note_spark Lyria 3 Clip (Preview) Generates 30s audio clips from text and image prompts.

audio_spark Lyria 2 Generates music from text prompts.

Language support

Gemini

All Gemini models can understand the following languages. Gemini models that are capable of text responses can also respond in these languages:

Afrikaans (af), Albanian (sq), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Azerbaijani (az), Basque (eu), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Catalan (ca), Cebuano (ceb), Chinese (Simplified and Traditional) (zh), Corsican (co), Croatian (hr), Czech (cs), Danish (da), Dhivehi (dv), Dutch (nl), English (en), Esperanto (eo), Estonian (et), Filipino (Tagalog) (fil), Finnish (fi), French (fr), Frisian (fy), Galician (gl), Georgian (ka), German (de), Greek (el), Gujarati (gu), Haitian Creole (ht), Hausa (ha), Hawaiian (haw), Hebrew (iw), Hindi (hi), Hmong (hmn), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Krio (kri), Kurdish (ku), Kyrgyz (ky), Lao (lo), Latin (la), Latvian (lv), Lithuanian (lt), Luxembourgish (lb), Macedonian (mk), Malagasy (mg), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Meiteilon (Manipuri) (mni-Mtei), Mongolian (mn), Myanmar (Burmese) (my), Nepali (ne), Norwegian (no), Nyanja (Chichewa) (ny), Odia (Oriya) (or), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Samoan (sm), Scots Gaelic (gd), Serbian (sr), Sesotho (st), Shona (sn), Sindhi (sd), Sinhala (Sinhalese) (si), Slovak (sk), Slovenian (sl), Somali (so), Spanish (es), Sundanese (su), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Urdu (ur), Uyghur (ug), Uzbek (uz), Vietnamese (vi), Welsh (cy), Xhosa (xh), Yiddish (yi), Yoruba (yo), and Zulu (zu).

Gemma

Gemma and Gemma 2 support only the English (en) language. Gemma 3 and Gemma 3n provide multilingual support in over 140 languages.

Embeddings

Multilingual text embedding models support the following languages:

Afrikaans (af), Albanian (sq), Amharic (am), Arabic (ar), Armenian (hy), Azerbaijani (az), Basque (eu), Belarusian (be), Bengali (bn), Bulgarian (bg), Catalan (ca), Cebuano (ceb), Chinese (Simplified and Traditional) (zh), Corsican (co), Czech (cs), Danish (da), Dutch (nl), English (en), Esperanto (eo), Estonian (et), Filipino (Tagalog) (fil), Finnish (fi), French (fr), Frisian (fy), Galician (gl), Georgian (ka), German (de), Greek (el), Gujarati (gu), Haitian Creole (ht), Hausa (ha), Hawaiian (haw), Hebrew (iw), Hindi (hi), Hmong (hmn), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kurdish (ku), Kyrgyz (ky), Lao (lo), Latin (la), Latvian (lv), Lithuanian (lt), Luxembourgish (lb), Macedonian (mk), Malagasy (mg), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Myanmar (Burmese) (my), Nepali (ne), Nyanja (Chichewa) (ny), Norwegian (no), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Samoan (sm), Scots Gaelic (gd), Serbian (sr), Sesotho (st), Shona (sn), Sindhi (sd), Sinhala (Sinhalese) (si), Slovak (sk), Slovenian (sl), Somali (so), Spanish (es), Sundanese (su), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Xhosa (xh), Yiddish (yi), Yoruba (yo), and Zulu (zu).

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 Gemini Enterprise Agent Platform, 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.