{ "models": [ { "name": "models/embedding-gecko-001", "version": "001", "displayName": "Embedding Gecko", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 1024, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedText", "countTextTokens" ] }, { "name": "models/gemini-2.5-flash", "version": "001", "displayName": "Gemini 2.5 Flash", "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-pro", "version": "2.5", "displayName": "Gemini 2.5 Pro", "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.0-flash-exp", "version": "2.0", "displayName": "Gemini 2.0 Flash Experimental", "description": "Gemini 2.0 Flash Experimental", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "bidiGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash", "version": "2.0", "displayName": "Gemini 2.0 Flash", "description": "Gemini 2.0 Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-001", "version": "2.0", "displayName": "Gemini 2.0 Flash 001", "description": "Stable version of Gemini 2.0 Flash, our fast and versatile multimodal model for scaling across diverse tasks, released in January of 2025.", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-exp-image-generation", "version": "2.0", "displayName": "Gemini 2.0 Flash (Image Generation) Experimental", "description": "Gemini 2.0 Flash (Image Generation) Experimental", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "bidiGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-lite-001", "version": "2.0", "displayName": "Gemini 2.0 Flash-Lite 001", "description": "Stable version of Gemini 2.0 Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-lite", "version": "2.0", "displayName": "Gemini 2.0 Flash-Lite", "description": "Gemini 2.0 Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-lite-preview-02-05", "version": "preview-02-05", "displayName": "Gemini 2.0 Flash-Lite Preview 02-05", "description": "Preview release (February 5th, 2025) of Gemini 2.0 Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-2.0-flash-lite-preview", "version": "preview-02-05", "displayName": "Gemini 2.0 Flash-Lite Preview", "description": "Preview release (February 5th, 2025) of Gemini 2.0 Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 40, "maxTemperature": 2 }, { "name": "models/gemini-exp-1206", "version": "2.5-exp-03-25", "displayName": "Gemini Experimental 1206", "description": "Experimental release (March 25th, 2025) of Gemini 2.5 Pro", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-flash-preview-tts", "version": "gemini-2.5-flash-exp-tts-2025-05-19", "displayName": "Gemini 2.5 Flash Preview TTS", "description": "Gemini 2.5 Flash Preview TTS", "inputTokenLimit": 8192, "outputTokenLimit": 16384, "supportedGenerationMethods": [ "countTokens", "generateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, { "name": "models/gemini-2.5-pro-preview-tts", "version": "gemini-2.5-pro-preview-tts-2025-05-19", "displayName": "Gemini 2.5 Pro Preview TTS", "description": "Gemini 2.5 Pro Preview TTS", "inputTokenLimit": 8192, "outputTokenLimit": 16384, "supportedGenerationMethods": [ "countTokens", "generateContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2 }, { "name": "models/gemma-3-1b-it", "version": "001", "displayName": "Gemma 3 1B", "inputTokenLimit": 32768, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemma-3-4b-it", "version": "001", "displayName": "Gemma 3 4B", "inputTokenLimit": 32768, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemma-3-12b-it", "version": "001", "displayName": "Gemma 3 12B", "inputTokenLimit": 32768, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemma-3-27b-it", "version": "001", "displayName": "Gemma 3 27B", "inputTokenLimit": 131072, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemma-3n-e4b-it", "version": "001", "displayName": "Gemma 3n E4B", "inputTokenLimit": 8192, "outputTokenLimit": 2048, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemma-3n-e2b-it", "version": "001", "displayName": "Gemma 3n E2B", "inputTokenLimit": 8192, "outputTokenLimit": 2048, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64 }, { "name": "models/gemini-flash-latest", "version": "Gemini Flash Latest", "displayName": "Gemini Flash Latest", "description": "Latest release of Gemini Flash", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-flash-lite-latest", "version": "Gemini Flash-Lite Latest", "displayName": "Gemini Flash-Lite Latest", "description": "Latest release of Gemini Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-pro-latest", "version": "Gemini Pro Latest", "displayName": "Gemini Pro Latest", "description": "Latest release of Gemini Pro", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-flash-lite", "version": "001", "displayName": "Gemini 2.5 Flash-Lite", "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-flash-image", "version": "2.0", "displayName": "Nano Banana", "description": "Gemini 2.5 Flash Preview Image", "inputTokenLimit": 32768, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1 }, { "name": "models/gemini-2.5-flash-preview-09-2025", "version": "Gemini 2.5 Flash Preview 09-2025", "displayName": "Gemini 2.5 Flash Preview Sep 2025", "description": "Gemini 2.5 Flash Preview Sep 2025", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-flash-lite-preview-09-2025", "version": "2.5-preview-09-25", "displayName": "Gemini 2.5 Flash-Lite Preview Sep 2025", "description": "Preview release (Septempber 25th, 2025) of Gemini 2.5 Flash-Lite", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-3-pro-preview", "version": "3-pro-preview-11-2025", "displayName": "Gemini 3 Pro Preview", "description": "Gemini 3 Pro Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-3-flash-preview", "version": "3-flash-preview-12-2025", "displayName": "Gemini 3 Flash Preview", "description": "Gemini 3 Flash Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens", "createCachedContent", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-3-pro-image-preview", "version": "3.0", "displayName": "Nano Banana Pro", "description": "Gemini 3 Pro Image Preview", "inputTokenLimit": 131072, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1, "thinking": true }, { "name": "models/nano-banana-pro-preview", "version": "3.0", "displayName": "Nano Banana Pro", "description": "Gemini 3 Pro Image Preview", "inputTokenLimit": 131072, "outputTokenLimit": 32768, "supportedGenerationMethods": [ "generateContent", "countTokens", "batchGenerateContent" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 1, "thinking": true }, { "name": "models/gemini-robotics-er-1.5-preview", "version": "1.5-preview", "displayName": "Gemini Robotics-ER 1.5 Preview", "description": "Gemini Robotics-ER 1.5 Preview", "inputTokenLimit": 1048576, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/gemini-2.5-computer-use-preview-10-2025", "version": "Gemini 2.5 Computer Use Preview 10-2025", "displayName": "Gemini 2.5 Computer Use Preview 10-2025", "description": "Gemini 2.5 Computer Use Preview 10-2025", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/deep-research-pro-preview-12-2025", "version": "deepthink-exp-05-20", "displayName": "Deep Research Pro Preview (Dec-12-2025)", "description": "Preview release (December 12th, 2025) of Deep Research Pro", "inputTokenLimit": 131072, "outputTokenLimit": 65536, "supportedGenerationMethods": [ "generateContent", "countTokens" ], "temperature": 1, "topP": 0.95, "topK": 64, "maxTemperature": 2, "thinking": true }, { "name": "models/embedding-001", "version": "001", "displayName": "Embedding 001", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 2048, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent" ] }, { "name": "models/text-embedding-004", "version": "004", "displayName": "Text Embedding 004", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 2048, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent" ] }, { "name": "models/gemini-embedding-exp-03-07", "version": "exp-03-07", "displayName": "Gemini Embedding Experimental 03-07", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 8192, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens" ] }, { "name": "models/gemini-embedding-exp", "version": "exp-03-07", "displayName": "Gemini Embedding Experimental", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 8192, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens" ] }, { "name": "models/gemini-embedding-001", "version": "001", "displayName": "Gemini Embedding 001", "description": "Obtain a distributed representation of a text.", "inputTokenLimit": 2048, "outputTokenLimit": 1, "supportedGenerationMethods": [ "embedContent", "countTextTokens", "countTokens", "asyncBatchEmbedContent" ] }, { "name": "models/aqa", "version": "001", "displayName": "Model that performs Attributed Question Answering.", "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.", "inputTokenLimit": 7168, "outputTokenLimit": 1024, "supportedGenerationMethods": [ "generateAnswer" ], "temperature": 0.2, "topP": 1, "topK": 40 }, { "name": "models/imagen-4.0-generate-preview-06-06", "version": "01", "displayName": "Imagen 4 (Preview)", "description": "Vertex served Imagen 4.0 model", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predict" ] }, { "name": "models/imagen-4.0-ultra-generate-preview-06-06", "version": "01", "displayName": "Imagen 4 Ultra (Preview)", "description": "Vertex served Imagen 4.0 ultra model", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predict" ] }, { "name": "models/imagen-4.0-generate-001", "version": "001", "displayName": "Imagen 4", "description": "Vertex served Imagen 4.0 model", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predict" ] }, { "name": "models/imagen-4.0-ultra-generate-001", "version": "001", "displayName": "Imagen 4 Ultra", "description": "Vertex served Imagen 4.0 ultra model", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predict" ] }, { "name": "models/imagen-4.0-fast-generate-001", "version": "001", "displayName": "Imagen 4 Fast", "description": "Vertex served Imagen 4.0 Fast model", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predict" ] }, { "name": "models/veo-2.0-generate-001", "version": "2.0", "displayName": "Veo 2", "description": "Vertex served Veo 2 model. Access to this model requires billing to be enabled on the associated Google Cloud Platform account. Please visit https://console.cloud.google.com/billing to enable it.", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ] }, { "name": "models/veo-3.0-generate-001", "version": "3.0", "displayName": "Veo 3", "description": "Veo 3", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ] }, { "name": "models/veo-3.0-fast-generate-001", "version": "3.0", "displayName": "Veo 3 fast", "description": "Veo 3 fast", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ] }, { "name": "models/veo-3.1-generate-preview", "version": "3.1", "displayName": "Veo 3.1", "description": "Veo 3.1", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ] }, { "name": "models/veo-3.1-fast-generate-preview", "version": "3.1", "displayName": "Veo 3.1 fast", "description": "Veo 3.1 fast", "inputTokenLimit": 480, "outputTokenLimit": 8192, "supportedGenerationMethods": [ "predictLongRunning" ] } ], "nextPageToken": "CiRtb2RlbHMvdmVvLTMuMS1mYXN0LWdlbmVyYXRlLXByZXZpZXc=" }