为您提供更透明的Gemini API成本管理与控制。
内容总结：
谷歌AI Studio推出成本管理新功能，助力开发者精准控制Gemini API开支
为提升API服务成本透明度与管理效率，谷歌近日在AI Studio平台推出一系列更新，重点推出“项目支出上限”功能，并全面升级用量分级体系。
项目支出上限：实现精细化成本管控
开发者现可为每个项目设置月度美元支出限额，该限额在手动调整前持续有效，特别适合多项目管理场景。设置生效存在约10分钟延迟，此期间产生的超额费用需由用户承担。用户可在AI Studio的“支出”标签页下进行配置。
用量分级体系升级：扩容更便捷透明
新版用量分级系统通过三项优化提升使用体验：降低高等级用量门槛，允许信用良好的用户更快获得更高配额；根据用量增长与支付记录自动升级用户层级；为每个层级设置账单账户级月度支出上限，该系统定义上限随层级提升自动增加，与用户自定义的项目支出上限相互独立。
账单流程优化：可视化与管控能力增强
近期AI Studio已陆续推出多项功能改进：
- 支持在平台内直接配置账单并关联项目，简化流程
- 新增速率限制仪表盘，可监控每分钟请求数、令牌数及每日请求数等关键指标
- 账单仪表盘内新增每日成本分解图表，支持按项目、时间范围和模型筛选查看
- 用量仪表盘扩展系统性能视图，新增错误指标、令牌用量统计及文生图、视频生成等专用图表
谷歌表示，此次更新旨在为开发者提供更可靠、透明的服务体验，未来将持续完善平台功能。
中文翻译：
为您提供更透明的 Gemini API 成本管理与控制
今天我们宣布在 Google AI Studio 中推出"项目支出上限"功能，让您能精准控制每月 Gemini API 的开销。同时，我们全面升级了用量阶梯体系，助您更快速地扩展业务，并保障 API 服务的公平使用。
项目支出上限：精细化成本管理
通过项目支出上限功能，您现在可以轻松为 Google AI Studio 中的每个项目设置每月 Gemini API 的美元支出限额。配置后，该限额将持续生效直至您主动修改或关闭，确保您对成本保持持续掌控。这对于拥有多个项目的账户尤其实用，您可以实现项目级的精细化支出管理。支出上限生效约有10分钟延迟，此期间产生的超额费用需由用户自行承担。
项目所有者现在可前往 AI Studio 的"支出"标签页，在"每月支出上限"栏目下为每个项目单独设置支出上限。
用量阶梯：扩展更顺畅，透明度再提升
我们彻底重构了用量阶梯体系，助您更快获得更高容量。虽然我们仍通过阶梯体系管理总体负载并保障 API 公平访问，但现在的阶梯升级过程已实现自动化且完全透明。主要变更包括：
- 降低升级门槛：为让拥有良好支付记录的用户更易获得更高配额，我们降低了高阶用量阶梯的支出要求。
- 自动快速升级：系统将根据用量增长和支付记录情况自动将您升级至更高阶梯。满足条件后，您将立即获得更高的速率限制和月度配额。
- 结算账户阶梯上限：每个用量阶梯现在将为整个结算账户设置月度支出上限（行业通用做法）。该系统定义的上限会随您升至更高阶梯而自动提高，且独立于您自定义的项目支出上限。
您可以在文档中查看用量阶梯限制与新标准，并直接在 Google AI Studio 中了解不同阶梯对速率限制指标的具体影响。
增强可观测性与控制的计费流程优化
过去几个月，我们在 Google AI Studio 中推出了一系列更新，以改进计费体验、可观测性与成本管理，旨在为开发者提供更便捷透明的付费服务体验。最新改进包括：
- 内置全新计费设置：现在可直接在设置中配置结算资料并关联项目，确保应用能随需求增长无缝扩展，无需在多个窗口和标签页间反复切换。
- 全新速率限制仪表板：清晰展示导入 Google AI Studio 的每个项目在速率限制方面的使用进度。您可监控三大关键指标：每分钟请求数（RPM）、每分钟令牌数（TPM）和每日请求数（RPD），通过可筛选图表识别流量峰值，并查看不同模型的速率限制。
- 全新成本仪表板：为帮助您管理预算，我们在结算仪表板中新增了每日成本细分图表。该工具透明展示支出情况，支持按项目追踪不同时间段（最近7天至整月）的成本，并可按模型筛选。
- 全新用量仪表板：提供更全面的系统性能视图。除标准请求计数外，您现在可深入查看错误指标、令牌用量及具体生成统计数据。我们还新增了针对 Imagen 和 Veo 每日请求量的专属图表，以及 Google 搜索与地图联网等工具的可视化数据。
我们希望这些更新能助您更自信地使用 Gemini API 进行开发。我们将持续改进，为您提供更可靠、更透明的服务。
英文来源：
Giving you more transparency and control over your Gemini API costs
Today, we are announcing Project Spend Caps in Google AI Studio to give you precise control over your monthly Gemini API expenses. We are also revamping our Usage Tiers to enable you to scale faster and help ensure fair access to our API service.
Project Spend Caps: Granular control for better cost management
With Project Spend Caps, you can now easily establish a monthly dollar limit for Gemini API spend on your projects in Google AI Studio. Once configured, this limit remains active until you choose to modify or disable it, ensuring consistent oversight of your costs. This is particularly useful for accounts with multiple projects where you’d want granular control over project-level spend. Spend caps have a ~10 minute delay and users are responsible for overages incurred during that period.
Project owners can now set these spend caps per project in AI Studio by going to the Spend tab, under “Monthly spend cap.”
Setup your monthly spend caps by project in the Spend tab in Google AI Studio
Usage Tiers: Less friction and more transparency as you scale
We’ve completely revamped our Usage Tiers to get you higher capacity faster. While we rely on these tiers to manage aggregate load and help to ensure equitable API access, your progression through them is now automated and transparent. Here is what’s changing:
- Lower spend qualifications: To make it easier for users with a strong payment history to get higher quotas, we are also reducing the spend qualifications for higher tiers.
- Automatic and faster upgrades: The system now automatically upgrades you to the next tier as your usage grows and your payment history matures. You get access to higher rate limits and increased monthly quota as soon as the criteria is met.
- Billing account tier cap: Each Usage Tier will now have a maximum monthly spend limit ($) enforced across your entire billing account (similar to other platforms in the industry). This system-defined cap automatically increases as you graduate to higher tiers, and operates independently of the custom Project Spend Caps you set yourself.
You can see the usage tier limits along with the new criteria in our docs and discover how different tiers impact your rate limit metrics directly within Google AI Studio.
Improved billing flow with enhanced observability and control
Over the past few months, we’ve launched a suite of updates in Google AI Studio to improve our billing experience, observability and cost management, with the goal to give developers an easier and more transparent experience with our paid services. Here’s what’s new: - New billing setup directly in Google AI Studio: You can now configure your billing profile and link it to your projects right from the settings, ensuring you can scale your application more seamlessly as your needs grow. No more jumping between 3 different windows and tabs.
- New rate limit dashboard: The dashboard gives you a clear view of your progress towards rate limits for every project imported into Google AI Studio. You can monitor usage against three key metrics: Requests Per Minute (RPM), Tokens Per Minute (TPM) and Requests Per Day (RPD), view and filter graphs for these metrics to identify traffic spikes and explore rate limits across different models.
- New cost dashboard: To help you manage your budget, we also launched a Daily Cost Breakdown Graph within the Billing Dashboard. This tool provides a transparent view of your spend, allowing you to track costs per project over different time frames — from the last 7 days to the entire month, and filter by model.
- New usage dashboard: An expanded, comprehensive view of your system's performance. Beyond standard request counts, you can now dive into error metrics, token usage and specific generation stats. We’ve also added dedicated graphs for Imagen and Veo requests per day, in addition to tools like Grounding with Google Search and Maps.
We hope these updates help you build more confidently with the Gemini API, and we will continue to make improvements to provide a more reliable and transparent service.