[null,null,["最后更新时间 (UTC):2025-08-19。"],[],[],null,["\u003cbr /\u003e\n\n\n|-------------------------------------------------------------------------------------------------------------------------------------|\n| *Click your Gemini API provider to view provider-specific content and code on this page.* Gemini Developer API Vertex AI Gemini API |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\nWhen you make a request to a generative model, you send along a *prompt* with\nyour request. By carefully crafting these prompts, you can influence the model\nto generate output specific to your needs.\n\nPrompting for Gemini models\n\nPrompts for Gemini models can contain questions,\ninstructions, contextual information, few-shot examples, and partial input for\nthe model to complete or continue.\n\nLearn about prompt design in the Gemini Developer API documentation:\n\n- [Prompt design strategies](https://ai.google.dev/gemini-api/docs/prompting-strategies)\n\n- [Prompt samples](https://ai.google.dev/gemini-api/prompts)\n\n| **Tip:** You can experiment with prompts and model configurations and rapidly iterate using [Google AI Studio](https://aistudio.google.com).\n\nPrompting for Imagen models\n\nFor Imagen, learn about\n[specific prompting strategies and options](https://ai.google.dev/gemini-api/docs/imagen#imagen-prompt-guide)\n\nOther options to control content generation\n\n- Configure [model parameters](/docs/ai-logic/model-parameters) to control how the model generates a response. For Gemini models, these parameters include max output tokens, temperature, topK, and topP. For Imagen models, these include aspect ratio, person generation, watermarking, etc.\n- Use [safety settings](/docs/ai-logic/safety-settings) to adjust the likelihood of getting responses that may be considered harmful, including hate speech and sexually explicit content.\n- Set [system instructions](/docs/ai-logic/system-instructions) to steer the behavior of the model. This feature is like a preamble that you add before the model gets exposed to any further instructions from the end user.\n- Pass a [*response schema*](/docs/ai-logic/generate-structured-output) along with the prompt to specify a specific output schema. This feature is most commonly used when [generating JSON output](/docs/ai-logic/generate-structured-output#generate-json-basic), but it can also be used for [classification tasks](/docs/ai-logic/generate-structured-output#generate-enum-basic) (like when you want the model to use specific labels or tags)."]]