← Back to Hub
Gemini-3-Flash
Commercial useGemini 3 Flash is a high-performance large language model developed by Google DeepMind, designed to deliver frontier-level reasoning with low latency and high throughput. It demonstrates strong performance across reasoning, multimodal understanding, and agentic benchmarks while supporting up to a 1M-token context window, making it well suited for real-time, high-concurrency, and production-scale AI workloads.
Pricing theo tokenInput 60 credits / 1M (≈ $0.30)Output 500 credits / 1M (≈ $2.50)
24 小时状态暂无活动
19:00–20:00
暂无数据
20:00–21:00
暂无数据
21:00–22:00
暂无数据
22:00–23:00
暂无数据
23:00–00:00
暂无数据
00:00–01:00
暂无数据
01:00–02:00
暂无数据
02:00–03:00
暂无数据
03:00–04:00
暂无数据
04:00–05:00
暂无数据
05:00–06:00
暂无数据
06:00–07:00
暂无数据
07:00–08:00
暂无数据
08:00–09:00
暂无数据
09:00–10:00
暂无数据
10:00–11:00
暂无数据
11:00–12:00
暂无数据
12:00–13:00
暂无数据
13:00–14:00
暂无数据
14:00–15:00
暂无数据
15:00–16:00
暂无数据
16:00–17:00
暂无数据
17:00–18:00
暂无数据
18:00–19:00
暂无数据
Input
Used to describe the generated output.
按 token 计费 (in 60 · out 500 cr / 1M)
Output
output typetext
Ready to create
Fill the inputs and click Run.
示例
点击示例将其加载到演练场并试用。
README
Gemini-3-Flash API
Gemini 3 Flash is a high-performance large language model developed by Google DeepMind, designed to deliver frontier-level reasoning with low latency and high throughput. It demonstrates strong performance across reasoning, multimodal understanding, and agentic benchmarks while supporting up to a 1M-token context window, making it well suited for real-time, high-concurrency, and production-scale AI workloads.
能力
- ✓ chat
如何在 CinAPI 上使用
- 1创建 API 密钥. 前往 API 密钥页面，为您的应用创建 hal_… 密钥。
- 2在演练场试用. 填写演练场选项卡中的表单并点击运行，即可查看即时结果（扣除真实积分）。
- 3通过 API 调用. 携带 Bearer 密钥 POST 到 /v1/claude，将其集成到您的产品中。
- 4集成与扩展. 一个密钥适用于所有模型（文本 / 图像 / 视频）。在控制台追踪用量和日志。
定价
每次运行 10 积分（≈ $0.05）。积分永不过期；在账单页面充值。部分模型按参数（分辨率、时长）定价——运行前价格会在运行按钮上实时更新。
常见问题
注册 CinAPI 账户，在 API 密钥下创建 API 密钥，然后携带 Bearer 密钥调用端点。新账户获得 200 免费积分。
chat