供应商简介: Google — Google Gemini 系列以百万 Token 上下文窗口、原生图像和音频理解能力引领多模态前沿,通过 Vertex AI 深度整合 Google 的研究基础设施。
← 全部供应商Google
美国17 个模型
Gemini — 超百万 Token 上下文的多模态智能
Google Gemini 系列以百万 Token 上下文窗口、原生图像和音频理解能力引领多模态前沿,通过 Vertex AI 深度整合 Google 的研究基础设施。
- ✓Gemini 2.5 Pro 提供超百万 Token 上下文和原生多模态理解
- ✓在编程、推理和长文档分析方面性能领先
- ✓通过 Vertex AI 支持原生图像、音频和视频输入
- ✓依托 Google 深厚研究基础设施保障稳定性
多模态超长上下文视觉理解音频处理代码生成
快速开始
from openai import OpenAI
client = OpenAI(
base_url="https://api.therouter.ai/v1",
api_key="YOUR_THEROUTER_KEY",
)
response = client.chat.completions.create(
model="google/gemini-2.5-pro",
messages=[{"role": "user", "content": "分析此代码是否存在安全漏洞"}],
max_tokens=1024,
)
print(response.choices[0].message.content)模型
Gemini 2.0 FlashWorkhorse model for all daily tasks. Strong overall performance and low latency supports real-time applications. Suitable for chat interactions, content generation, and general-purpose AI tasks.Gemini 2.0 Flash LiteGoogle's cost-effective Gemini model to support high throughput. Optimized for the most price-sensitive use cases while maintaining solid quality for everyday tasks.Gemini 2.5 FlashBest for balancing reasoning and speed. Gemini 2.5 Flash offers thinking capabilities with strong performance across coding, math, and reasoning tasks at an efficient price point.Gemini 2.5 Flash Image PreviewImage generation model built on Gemini 2.5 Flash with conversational, multi-turn editing capabilities. Supports text and image input/output for creative workflows.Gemini 2.5 Flash LiteMost balanced Gemini model for low latency use cases. Optimized for high-volume, cost-sensitive workloads with strong quality at minimal cost.Gemini 2.5 Flash Lite Preview 09-2025Most balanced Gemini model for low latency use cases. A preview snapshot of Gemini 2.5 Flash Lite optimized for speed and cost efficiency.Gemini 2.5 Flash Preview 09-2025Strong overall performance and low latency. A preview snapshot of Gemini 2.5 Flash with balanced reasoning and speed.Gemini 2.5 ProStrongest Gemini model quality, especially for code and complex prompts. Features advanced reasoning with thinking capabilities and excels at multi-step problem solving, code generation, and mathematical reasoning.
常见问题
TheRouter 提供哪些 Gemini 模型?
TheRouter 提供 Gemini 2.5 Pro、Gemini 2.5 Flash、Gemini 2.0 Flash 及多个其他 Gemini 变体,均通过标准的 google/模型名称 格式访问。
TheRouter 是否支持 Gemini 的百万 Token 上下文?
支持。TheRouter 将长上下文请求原样传递至 Vertex AI。注意:超过 20 万 Token 的提示词可能适用长上下文定价。
TheRouter 如何连接 Google 模型?
TheRouter 通过 us-central1 的专用 Vertex AI 供应商服务路由 Google 模型请求。每次请求均为直接 API 调用,无中间商。
能通过 TheRouter 向 Gemini 发送图片吗?
可以。TheRouter 的多模态管道会获取图片 URL,转换为 base64 内联数据,并以所需格式发送至 Vertex AI,支持 JPEG、PNG、GIF、WebP 等格式。