Repository Public
1This guide introduces all the models available through the Gemini API.23*** ** * ** ***45## Gemini 367### Stable89[### Gemini 3.8 Flash10Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.11New Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash) [### Gemini 3.8 Live12Default Live API model for most low-latency voice agent experiences without reasoning delays.13New Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live) [### Gemini 3.8 Live Extended Thinking14High-reasoning Live API model for voice interactions, recommended when higher background reasoning is required.15New Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking) [### Gemini 3.7 Flash16Our previous-generation Flash model for complex coding, agentic workflows, and reliable multi-step execution.17Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash) [### Gemini 3.6 Flash18Our previous-generation Flash model, balancing speed and multimodal capabilities across general agentic and everyday tasks.19Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash) [### Gemini 3.5 Flash20Our legacy Flash model, providing baseline speed and foundational performance for routine, high-throughput workloads.21Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash) [### Gemini 3.5 Flash-Lite22Our fastest, most cost-effective 3.5 model for high-throughput execution.23Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite) [### Gemini 3.1 Flash-Lite24Frontier-class performance rivaling larger models at a fraction of the cost.25Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite) [### Nano Banana 226Powerful, high-efficiency image generation and editing, optimized for speed and high-volume use cases.27Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image) [### Nano Banana 2 Lite28Ultra-low latency and cost-effective image generation and editing, designed for high-volume interactive use cases.29Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-image) [### Nano Banana Pro30State-of-the-art image generation and editing models for highly contextual native image creation.31Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image) [### Gemini 3.5 Transcribe32Low-latency speech-to-text model with utterance-based language detection, speaker diarization, and word timestamps.33New Stable](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe)3435### Preview3637[### Gemini 3.1 Pro38Advanced intelligence, complex problem-solving skills, and powerful agentic and vibe coding capabilities.39Preview](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview) [### Gemini 3 Flash40Frontier-class performance rivaling larger models at a fraction of the cost.41Preview](https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview) [### Gemini 3.5 Live Translate42Low-latency, real-time speech to speech translation model that supports 70+ languages.43New](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-live-translate-preview) [### Gemini 3.1 Flash Live44Legacy Live API preview model. We recommend updating to Gemini 3.8 Live.45New](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview) [### Gemini 3.1 Flash TTS46Powerful, low-latency speech generation.47New](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview) [### Gemini Omni Flash48Fast video generation, editing, keyframe interpolation, and extension with native audio.49New](https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash)5051### All Gemini 3 models5253| Model | Endpoint |54|---|---|55| [Gemini 3.8 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash) | ``` gemini-3.8-flash ``` |56| [Gemini 3.8 Live](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live) | ``` gemini-3.8-live ``` |57| [Gemini 3.8 Live Extended Thinking](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking) | ``` gemini-3.8-live-extended-thinking ``` |58| [Gemini 3.7 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash) | ``` gemini-3.7-flash ``` |59| [Gemini 3.6 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash) | ``` gemini-3.6-flash ``` |60| [Gemini 3.5 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash) | ``` gemini-3.5-flash ``` |61| [Gemini 3.5 Flash-Lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite) | ``` gemini-3.5-flash-lite ``` |62| [Gemini 3.1 Flash-Lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite) | ``` gemini-3.1-flash-lite ``` |63| [Nano Banana 2](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image) | ``` gemini-3.1-flash-image ``` |64| [Nano Banana 2 Lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-image) | ``` gemini-3.1-flash-lite-image ``` |65| [Nano Banana Pro](https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image) | ``` gemini-3-pro-image ``` |66| [Gemini 3.1 Pro](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview) | ``` gemini-3.1-pro-preview ``` |67| [Gemini 3 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-3-flash-preview) | ``` gemini-3-flash-preview ``` |68| [Gemini 3.5 Live Translate](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-live-translate-preview) | ``` gemini-3.5-live-translate-preview ``` |69| [Gemini 3.1 Flash Live](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview) | ``` gemini-3.1-flash-live-preview ``` |70| [Gemini 3.1 Flash TTS](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview) | ``` gemini-3.1-flash-tts-preview ``` |71| [Gemini Omni Flash](https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash) | ``` gemini-omni-1.1-flash ``` |72| [Gemini 3.5 Transcribe](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe) | ``` gemini-3.5-transcribe gemini-3.5-transcribe-live ``` |7374## Gemini 2.5 Flash7576| Model | Description | Endpoint |77|---|---|---|78| [Gemini 2.5 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash) | Our best price-performance model for low-latency, high-volume tasks that require reasoning. | ``` gemini-2.5-flash ``` |79| [Nano Banana](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image) | State-of-the-art native image generation and editing designed for fast, creative workflows. | ``` gemini-2.5-flash-image ``` |80| [Gemini 2.5 Flash Live](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025) | Optimized for real-time conversational agents with sub-second native audio streaming. | ``` gemini-2.5-flash-native-audio-preview-12-2025 ``` |81| [Gemini 2.5 Flash TTS](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts) | Controllable text-to-speech audio generation with fine control over style and pacing. | ``` gemini-2.5-flash-preview-tts ``` |8283## Gemini 2.5 Flash-Lite8485| Model | Description | Endpoint |86|---|---|---|87| [Gemini 2.5 Flash-Lite](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-lite) | The fastest and most budget-friendly multimodal model in the 2.5 family. | ``` gemini-2.5-flash-lite ``` |8889## Gemini 2.5 Pro9091| Model | Description | Endpoint |92|---|---|---|93| [Gemini 2.5 Pro](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro) | Our most advanced model for complex tasks, featuring deep reasoning and coding capabilities in the 2.5 family. | ``` gemini-2.5-pro ``` |94| [Gemini 2.5 Pro TTS](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts) | High-fidelity speech synthesis optimized for quality in structured workflows like podcasts and audiobooks. | ``` gemini-2.5-pro-preview-tts ``` |9596## Audio models9798*This section contains all audio models, including ones that may already be listed in other sections*99100| Model | Description | Endpoint |101|---|---|---|102| [Gemini 3.8 Live](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live) | The default option for most low-latency voice agent experiences and real-time dialogue without reasoning delays. | ``` gemini-3.8-live ``` |103| [Gemini 3.8 Live Extended Thinking](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live-extended-thinking) | Our high-reasoning audio-to-audio model, recommended when higher background reasoning is required during live interactions. | ``` gemini-3.8-live-extended-thinking ``` |104| [Gemini 3.1 Flash Live](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview) | Legacy audio-to-audio preview model. We recommend updating to Gemini 3.8 Live. | ``` gemini-3.1-flash-live-preview ``` |105| [Gemini 3.1 Flash TTS](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview) | Powerful, low-latency speech generation, with natural outputs, steerable prompts, and new expressive audio tags for precise narration control. | ``` gemini-3.1-flash-tts-preview ``` |106| [Gemini 3.5 Transcribe](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe) | Low-latency speech-to-text model with utterance-based language detection, speaker diarization, word-level timestamps, and custom vocabulary biasing. | ``` gemini-3.5-transcribe gemini-3.5-transcribe-live ``` |107| [Gemini 2.5 Flash Live](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-native-audio-preview-12-2025) | Our flagship Live API model for low-latency, bidirectional voice and video agents with native audio reasoning. | ``` gemini-2.5-flash-native-audio-preview-12-2025 ``` |108| [Gemini 2.5 Flash TTS](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts) | Fast and controllable text-to-speech for low-latency, cost-efficient applications and real-time assistants. | ``` gemini-2.5-flash-preview-tts ``` |109| [Gemini 2.5 Pro TTS](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts) | High-fidelity speech synthesis optimized for quality in structured workflows like podcasts and audiobooks. | ``` gemini-2.5-pro-preview-tts ``` |110111## Generative media models112113*This section contains all generative media models, including ones that may already be listed in other sections*114115| Model | Description | Endpoint |116|---|---|---|117| [Nano Banana 2](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image) | High-efficiency production-scale visual creation, combining the intelligence of the Gemini 3 series with lightning-fast generation speeds. | ``` gemini-3.1-flash-image ``` |118| [Nano Banana 2 Lite](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-image) | Designed as the efficiency specialist of the image generation family, offering ultra-low latency and cost-effective image generation and editing. | ``` gemini-3.1-flash-lite-image ``` |119| [Veo 3.1](https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview) | State-of-the-art cinematic video generation with advanced creative controls and natively synchronized audio. | ``` veo-3.1-generate-preview ``` |120| [Nano Banana Pro](https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image) | A professional design engine with a reasoning core for studio-quality 4K visuals, complex layouts, and precise text rendering. | ``` gemini-3-pro-image ``` |121| [Veo 3.1 Lite](https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview) | High-efficiency, low-cost, developer-first video generation, editing, and cinematic control from the Veo 3.1 family. | ``` veo-3.1-lite-generate-preview ``` |122| [Gemini Omni Flash](https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash) | Fast video generation, editing, keyframe interpolation, and extension with native audio. | ``` gemini-omni-1.1-flash ``` |123| [Nano Banana](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image) | State-of-the-art native image generation and editing designed for fast, creative workflows. | ``` gemini-2.5-flash-image ``` |124| Imagen 4 (Shut down) | Text-to-image model featuring fast and ultra-fast generation (shut down). | ``` imagen-4.0-generate ``` |125126## Music generation models127128*This section contains all music generation models, including ones that may already be listed in other sections*129130| Model | Description | Endpoint |131|---|---|---|132| [Lyria 3.5](https://ai.google.dev/gemini-api/docs/models/lyria-3.5) | Our flagship music generation model, optimized for full-length songs with complex structural coherence. | ``` lyria-3.5 ``` |133| [Lyria 3 Clip](https://ai.google.dev/gemini-api/docs/models/lyria-3-clip-preview) | Optimized for generating short musical clips, loops, and previews up to 30 seconds. | ``` lyria-3-clip-preview ``` |134| [Lyria 3 Pro](https://ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview) | Previous generation music generation model for full-length songs. | ``` lyria-3-pro-preview ``` |135| [Lyria RealTime](https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp) | High-fidelity music generation model providing granular creative control and real-time streaming capabilities. | ``` lyria-realtime-exp ``` |136137## Tool and agent models138139| Model | Description | Endpoint |140|---|---|---|141| [Computer Use](https://ai.google.dev/gemini-api/docs/models/gemini-2.5-computer-use-preview-10-2025) | A specialized model that can "see" a digital screen and perform UI actions like clicking, typing, and navigating to automate complex browser tasks. | ``` gemini-2.5-computer-use-preview-10-2025 ``` |142| [Gemini Deep Research](https://ai.google.dev/gemini-api/docs/models/deep-research-preview-04-2026) | An agentic model that autonomously plans and executes multi-step research across hundreds of sources to produce cited, interactive reports. | ``` deep-research-preview-04-2026 ``` |143| [Gemini Deep Research Max](https://ai.google.dev/gemini-api/docs/models/deep-research-max-preview-04-2026) | Maximum comprehensiveness for automated context gathering and synthesis across hundreds of sources. | ``` deep-research-max-preview-04-2026 ``` |144| [Antigravity Agent](https://ai.google.dev/gemini-api/docs/models/antigravity-preview-05-2026) | A general-purpose managed agent that autonomously plans, reasons, runs code, manages files, and browses the web inside a secure, isolated Linux sandbox. | ``` antigravity-preview-05-2026 ``` |145146## Specialized task models147148| Model | Description | Endpoint |149|---|---|---|150| [Gemini Embedding 2](https://ai.google.dev/gemini-api/docs/models/gemini-embedding-2) | Our first multimodal embedding model, mapping text, images, video, audio, and PDFs into a unified embedding space for advanced semantic search and RAG systems. | ``` gemini-embedding-2-preview ``` |151| [Gemini Embedding](https://ai.google.dev/gemini-api/docs/models/gemini-embedding-001) | High-dimensional vector representations for advanced semantic search, text classification, and RAG systems. | ``` gemini-embedding-001 ``` |152| [Gemini Robotics ER 2](https://ai.google.dev/gemini-api/docs/robotics-overview) | Embodied reasoning model delivering advanced video understanding, spatial reasoning, multi-step tool orchestration, and multi-robot collaboration for robotics tasks. | ``` gemini-robotics-er-2-preview ``` |153| [Gemini Robotics ER 1.6](https://ai.google.dev/gemini-api/docs/models/gemini-robotics-er-1.6-preview) | Advanced embodied reasoning model that understands physical spaces and plans multi-step tasks for robotic agents with new capabilities like instrument reading, improved spatial and physical reasoning. | ``` gemini-robotics-er-1.6-preview ``` |154155## Previous models156157> [!WARNING]158> These models are [deprecated](https://ai.google.dev/gemini-api/docs/deprecations) and will be shut down soon; migrate to newer models to prevent service interruptions.159160| Model | Description | Endpoint |161|---|---|---|162| [Gemini 2.0 Flash](https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash) (Shut down) | Our second generation workhorse model, with next-gen features and improved capabilities, including superior speed, native tool use, and a 1M token context window. | ``` gemini-2.0-flash ``` |163| [Gemini 2.0 Flash-Lite](https://ai.google.dev/gemini-api/docs/models/gemini-2.0-flash-lite) (Shut down) | Our fastest second generation model, optimized for cost efficiency and low latency. | ``` gemini-2.0-flash-lite ``` |164| [Gemini 3.1 Flash-Lite Preview](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-preview) (Shut down) | Our most cost-efficient multimodal model, offering the fastest performance for high-frequency, lightweight tasks. | ``` gemini-3.1-flash-lite-preview ``` |165| [Gemini 3 Pro Preview](https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-preview) (Shut down) | Our state-of-the-art reasoning model, with advanced multimodal understanding. | ``` gemini-3-pro-preview ``` |166167## Model version name patterns168169Gemini models are available in either *stable* , *preview* , *latest* , or170*experimental* versions.171172> [!NOTE]173> **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.174175### Stable176177Points to a specific stable model. Stable models usually don't change. Most178production apps should use a specific stable model.179180For example: `gemini-3.6-flash`.181182### Preview183184Points to a preview model which may be used for production. Preview models will185typically have billing enabled, might come with more restrictive rate limits and186will be deprecated with at least 2 weeks notice.187188For example: `gemini-2.5-flash-preview-09-2025`.189190### Latest191192Points to the latest release for a specific model variation. This can be a193stable, preview or experimental release. This alias will get hot-swapped with194every new release of a specific model variation. For breaking changes, a195**2-week notice** will be provided through email before the version behind196latest is changed.197198For example: `gemini-flash-latest`.199200### Experimental201202Points to an experimental model which will typically be not be suitable for203production use and come with more restrictive rate limits. We release204experimental models to gather feedback and get our latest updates into the hands205of developers quickly.206207Experimental models are not stable and availability of model endpoints is208subject to change.209210## Model deprecations211212For information about model deprecations, visit the [Gemini deprecations](https://ai.google.dev/gemini-api/docs/deprecations) page.