A partir de 29 de abril de 2025, os modelos Gemini 1.5 Pro e Gemini 1.5 Flash não estarão disponíveis em projetos que não os usaram antes, incluindo novos projetos. Para mais detalhes, consulte Versões e ciclo de vida do modelo.
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
O Gemini 2.5 Flash é nosso melhor modelo em termos de preço e desempenho e oferece recursos abrangentes. O Gemini 2.5 Flash é nosso primeiro modelo
Flash com capacidade de raciocínio,
que permite ver o processo de pensamento do modelo ao
gerar a resposta.
Para informações técnicas ainda mais detalhadas sobre o Gemini 2.5 Flash (como comparativos de performance, informações sobre nossos conjuntos de dados de treinamento, esforços de sustentabilidade, uso e limitações pretendidos e nossa abordagem de ética e segurança), consulte nosso relatório técnico sobre os modelos do Gemini 2.5 e a ficha do modelo do Gemini 2.5 Flash.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Informações incorretas ou exemplo de código","incorrectInformationOrSampleCode","thumb-down"],["Não contém as informações/amostras de que eu preciso","missingTheInformationSamplesINeed","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Outro","otherDown","thumb-down"]],["Última atualização 2025-08-25 UTC."],[],[],null,["# Gemini 2.5 Flash is our best model in terms of price and performance,\nand offers well-rounded capabilities. Gemini 2.5 Flash is our first\nFlash model that features [thinking capabilities](/vertex-ai/generative-ai/docs/thinking),\nwhich lets you see the thinking process that the model goes through when\ngenerating its response.\n\nFor even more detailed technical information on Gemini 2.5 Flash (such as\nperformance benchmarks, information on our training datasets, efforts on\nsustainability, intended usage and limitations, and our approach to ethics and\nsafety), see our [technical\nreport](https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf)\non our Gemini 2.5 models and the [model card for\nGemini 2.5 Flash](https://storage.googleapis.com/model-cards/documents/gemini-2.5-flash.pdf). \n\n2.5 Flash\n---------\n\n| **Note:** The `gemini-live-2.5-flash` version of Gemini 2.5 Flash is available as a private general availability offering. Reach out to your Google account team representative to request access.\n\n\n[Try in Vertex AI](https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.5-flash) [View in Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemini-2.5-flash) [(Preview) Deploy example app](https://console.cloud.google.com/vertex-ai/studio/multimodal?suggestedPrompt=How%20does%20AI%20work&deploy=true&model=gemini-2.5-flash)\nNote: To use the \"Deploy example app\" feature, you need a Google Cloud project with billing and Vertex AI API enabled.\n\n+ Supervised fine tuning not supported \n\\* Available for 128K context window only\n\nImage\n-----\n\n| **Preview**\n|\n|\n| This product or feature is a Generative AI Preview offering, subject to\n| the \"Pre-GA Offerings Terms\" of the\n| [Google Cloud Service Specific Terms](/terms/service-terms),\n| as well as the\n| [Additional Terms for Generative AI Preview Products](/trustedtester/aitos). For this\n| Generative AI Preview offering, Customers may elect to use it for\n| production or commercial purposes, or disclose Generated Output to\n| third-parties, and may process personal data as outlined in the\n| [Cloud Data Processing\n| Addendum](/terms/data-processing-addendum),\n| subject to the obligations and restrictions described in the agreement\n| under which you access Google Cloud. Pre-GA products are available \"as is\"\n| and might have limited support. For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\n\n[Try in Vertex AI](https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.5-flash-image-preview) [(Preview) Deploy example app](https://console.cloud.google.com/vertex-ai/studio/multimodal?suggestedPrompt=How%20does%20AI%20work&deploy=true&model=gemini-2.5-flash-image-preview)\nNote: To use the \"Deploy example app\" feature, you need a Google Cloud project with billing and Vertex AI API enabled.\n\nLive API native audio\n---------------------\n\n|\n| **Preview**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\n\nGemini 2.5 Flash with Live API native audio features\nour cutting-edge native audio functionality for\n[Live API](/vertex-ai/generative-ai/docs/live-api). In addition\nto the standard Live API features, this preview\nmodel includes:\n\n- **Enhanced voice quality and adaptability:** Live API native audio provides richer, more natural voice interactions with [30 HD voices](/text-to-speech/docs/chirp3-hd#voice_options) in [24 languages](/text-to-speech/docs/chirp3-hd#language_availability).\n- **Introducing Proactive Audio:** When Proactive Audio is enabled, the model only responds when it's relevant. The model generates text transcripts and audio responses proactively only for queries directed to the device, and does not respond to non-device directed queries.\n- **Introducing Affective Dialog:** Models using Live API native audio can understand and respond appropriately to users' emotional expressions for more nuanced conversations.\n\n\nFor more information on Live API, see our\n[standalone Live API documentation](/vertex-ai/generative-ai/docs/live-api).\n\n\n[Try in Vertex AI](https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-live-2.5-flash-preview-native-audio)"]]
