谷歌 Gemini API 免费额度 2026:Gemini 4 Hydrogen 与 3.8 Flash 免费开放Google Gemini API Free Tier 2026: Gemini 4 Hydrogen and 3.8 Flash Available for Free


AI free token/AI免费积分

谷歌 Gemini API 免费额度 2026:Gemini 4 Hydrogen 与 3.8 Flash 免费开放

本文来源:https://agentdeals.dev/vendor/google-gemini-api
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

Google Gemini API 免费层级包括 免费层级:Gemini 4 Hydrogen(免费层级中唯一的 Gemini 4 模型)、Gemini 3.8 Flash……已于 2026 年 11 月验证。可与 AI / ML 领域的 32 个替代方案进行比较。

AI / ML 领域的子类型:llm_api——厂商在自己的基础设施上运行语言或多模态模型,并按模型名称出售对它们的调用;你发送一个提示词,收到一段补全结果;embeddings_api——为文本或媒体返回一个向量,以便与其他向量比较;输出是向量,而非补全结果;speech_api——将录制或流式语音转换为文本,或将文本转换为语音。我们于 2026-09-01 从 https://ai.google.dev/pricing 读到这些内容,其中写道:"我们的 3.1 Flash Text-to-Speech 音频模型针对高性价比、低延迟、可控的语音生成进行了优化。"我们使用此信息的方式。

限制、定价历史和 32 个替代方案。已于 2026 年 11 月验证。最后更新于 2026-11-21。

Google Gemini API 的免费层级提供 免费层级:Gemini 4 Hydrogen(免费层级中唯一的 Gemini 4 模型)、Gemini 3.8 Flash、3.6 Flash、3.5 Flash-Lite……我们将其评为稳定。记录的 21 项变更中没有一项收紧了条款。最适合 ai / ml 工作负载——有 32 个替代方案可用。

免费层级:Gemini 4 Hydrogen(免费层级中唯一的 Gemini 4 模型)、Gemini 3.8 Flash、3.6 Flash、3.5 Flash-Lite、3.1 Flash-Lite、Gemini 3 Flash Preview、Gemini Embedding 2 和 Gemma 4 均免费。Gemini 4 Carbon、Gemini 4 Argon 和 Gemini 4 Neon 仅付费提供。同样免费的还有 Gemini 3.8 Live(实时语音)、Gemini 3.5 Live Translate(翻译)、Gemini 3.5 Transcribe(语音转文本)、Gemini 3.8 Flash TTS 和 Gemini 3.8 Flash-Lite TTS(文本转语音)。Gemini Decision(gemini-decision-1)于 2026-11-11 发布,是一个通过 Decisions API 提供的多模态决策模型。它以概率形式回答是/否、选择和量表(rubric)类问题,且不生成任何输出 token,因此没有输出价格;在免费层级输入免费,每天 10,000 次请求,在付费层级每百万输入 token 收费 $0.10。Gemini 4 Hydrogen(gemini-4-hydrogen)于 2026-11-12 发布,在 Gemini API 免费层级中输入、输出和上下文缓存均免费。在付费层级,Gemini 4 Hydrogen 每百万输入 token 收费 $1.50、每百万输出 token 收费 $7.50(输出包含思考 token),上下文缓存为 $0.075(仅限隐式缓存);在 Batch API 上,Gemini 4 Hydrogen 输入为 $0.75、输出为 $3.75。其他 Gemini 4 模型,Gemini 4 Carbon(gemini-4-carbon)、Gemini 4 Argon(gemini-4-argon)和 Gemini 4 Neon(gemini-4-neon)仅付费提供,Gemini 3.1 Pro Preview 和 Gemini Omni 1.2 Flash(gemini-omni-1.2-flash)也仅付费提供。Google 称 Gemini 4 Carbon 为其能力最强的推理模型,自 2026-11-10 起已正式可用,但不在 Gemini API 免费层级中提供。Gemini 4 Argon 自 2026-10-13 起正式可用,不在 Gemini API 免费层级中提供。Gemini 4 Neon(gemini-4-neon)自 2026-11-18 起正式可用,不在 Gemini API 免费层级中提供,付费层级每 100 万输入 token 收费 $3.00、每 100 万输出 token 收费 $15.00,Batch API 每 100 万输入 token 收费 $1.50、每 100 万输出 token 收费 $7.50。根据 ai.google.dev/gemini-api/docs/google-ai-plans,"Gemini 4 Argon 在免费方案中不可用。"Gemini 4 Argon 可通过付费层级的 Gemini API 使用。据 ai.google.dev/gemini-api/docs/google-ai-plans,"直接使用 Gemini API(例如使用 API 密钥或外部应用)将单独计费和管理,"根据 ai.google.dev/gemini-api/docs/google-ai-plans,Google AI Pro 和 Ultra 可在 Google AI Studio 中提供对 Gemini 4 Argon 的访问权限。Gemini 4 Argon 在 Google AI Ultra 和付费版 Google AI Pro 的 Antigravity 中提供。在 Google AI Studio 中,Gemini 4 Carbon 需要 Google AI Ultra 方案,且在免费版或 Google AI Pro 方案中不可用(aistudio.google.com/docs/google-ai-plans)。在 Google AI Studio 中,Gemini 4 Neon 在 Google AI Pro 和 AI Ultra 中可用,在免费方案中不可用。在 Antigravity 中,Gemini 4 Carbon 仅在 Google AI Ultra 和 Enterprise 中可用(antigravity.google/docs/models)。在 Google AI Pro 试用版中,Argon 仅在"在符合条件的高端设备上试用"时可用(antigravity.google/docs/models)。Claude Opus 5.5 和 Claude Sonnet 5.5 不包含在 Google AI Pro 试用版中;试用用户以及通过第三方合作伙伴、Pixel Pass 或 Google Fi 获得会员资格的用户,通过 Google One 管理订阅。通过 Jio 等合作伙伴优惠获得的 Google AI Pro 在 Antigravity 中不包含 Gemini 4 Argon、Claude Sonnet 5.5 或 Claude Opus 5.5。据 discuss.ai.google.dev 上一位 Google 员工(2026-10-21)称,"这些前沿模型仅限于直接付费(非试用/非促销)的 Google AI Pro、Google AI Ultra 和 Enterprise 方案。"在 API 中,没有任何 Gemini 图像模型提供免费层级。Nano Banana 2.1(gemini-nano-banana-2.1)于 2026-10-06 正式可用。其价格为每张 1K 图像 $0.0336、每张 2K 图像 $0.0504、每张 4K 图像 $0.113。Batch API 的价格为这些价格的一半。Nano Banana Pro 每张 1K 或 2K 图像收费 $0.134,每张 4K 图像收费 $0.24。除 Gemini Decision 外,Google 未公布免费层级的速率限制;每个项目的限制显示在 Google AI Studio 中。开发者报告称,截至 2026 年 9 月,429 错误显示 Gemini 3.x Flash 模型为每天 20 次请求,3.x Flash-Lite 模型为每天 500 次请求。速率限制按项目而非按 API 密钥适用。根据 Google 的速率限制页面,每日请求配额在太平洋时间午夜重置。自 2026-09-18 起,Google 仅向此前使用过 Gemini 2.5 模型的用户提供这些模型,并将新项目引导至 3.5 Flash-Lite 或 3.8 Flash。如果你的应用调用 gemini-3.7-flash,Google 已于 2026-10-08 弃用该模型。对 gemini-3.7-flash 的请求会自动路由到 gemini-3.8-flash。Google 表示应将模型字符串更新为 gemini-3.8-flash。现有用户可调用 gemini-2.5-pro 和 gemini-2.5-flash,直至 2026-12-01 Google 关闭这两款模型。自该日起,对 gemini-2.5-pro 的请求将路由至 gemini-3.8-flash,并按其费率计费。对 gemini-2.5-flash 的请求将路由至 gemini-3.5-flash-lite,并按其费率计费。请在 2026-12-01 前更新模型字符串,并查阅 Google 的迁移指南以应对破坏性 API 变更。gemini-2.5-flash-lite 未被弃用。如果你的应用调用 Gemini 3.5 Flash(gemini-3.5-flash),Google 已于 2026-10-08 弃用该模型。对 gemini-3.5-flash 的请求会自动路由至 gemini-3.6-flash。Google 表示应将模型字符串更新为 gemini-3.6-flash 或 gemini-3.8-flash。Google 于 2026-10-22 关闭了 Gemini Omni Flash Preview(gemini-omni-flash-preview)。Google 的替代方案是 gemini-omni-1.2-flash。Google 将于 2026 年 12 月 3 日关闭 Gemini Omni 1.1 Flash(gemini-omni-1.1-flash);此后,指明 gemini-omni-1.1-flash 的请求将由 gemini-omni-1.2-flash 按 Gemini Omni 1.2 Flash 的费率响应。Gemini 3.1 Flash-Lite(gemini-3.1-flash-lite)可调用至 2027-05-07,届时 Google 将关闭该模型。Google 的替代方案是 gemini-3.5-flash-lite。付费价格,每百万 token(输入/输出;输出价格包含思考 token):Gemini 4 Carbon $2/$10,截至 2026-11-30(上下文缓存 $0.10,之后 $0.20,仅限隐式缓存);Gemini 4 Argon $2/$10,截至 2026-11-30(上下文缓存 $0.10,之后 $0.20,仅限隐式缓存);Gemini 3.8 Flash $0.75/$3.75,直至 2026-12-31,然后从 2027-01-01 起输入 $1.50、输出 $7.50(3.6 Flash:相同价格和日期);Gemini 3.5 Flash-Lite(不是 gemini-3.5-flash)$0.30/$2.50;Gemini 3.1 Flash-Lite $0.25/$1.50;Gemini 3.1 Pro Preview $2/$12(提示词最多 200K token;超过 200K token 的提示词输入收费 $4、输出收费 $18)。截至 2026-11-30,对于最多 200K token 的提示词,Gemini 4 Argon 的 Standard 输出价格低于 Gemini 3.1 Pro Preview,且输入价格相同;从 2026-12-01 起 Argon 的价格更高。自 2026 年 12 月 1 日起,Gemini 4 Argon 的 Standard 价格为每百万输入 token $4、每百万输出 token $20,Batch API 输入 $2、输出 $10,Flex 输入 $2、输出 $10,Priority 输入 $7.20、输出 $36。自 2026 年 12 月 1 日起,Gemini 4 Carbon 的 Standard 价格也为每百万输入 token $4、每百万输出 token $20,Batch API 和 Flex 输入 $2、输出 $10,Priority 输入 $7.20、输出 $36。Batch API 的价格是标准价格的一半;Gemini 3.8 Flash 截至 2026-12-31 为每百万 token 输入 $0.375、输出 $1.875。Gemini 4 Carbon 和 Gemini 4 Argon 在 Batch API 上截至 2026-11-30 为输入 $1、输出 $5。Google 还出售两个层级,Flex 和 Priority,两者均处于 Preview 阶段。请求通过 service_tier 字段("flex" 或 "priority")选择一个层级;不带该字段时请求为 Standard。Gemini 4 Carbon 和 Gemini 4 Argon 在 Flex 上截至 2026-11-30 为输入 $1、输出 $5;在 Priority 上截至 2026-11-30 为输入 $3.60、输出 $18。"Gemini Flex API 是一个推理层级,相比标准费率可降低成本 50%,代价是可变延迟和尽力而为的可用性"(ai.google.dev/gemini-api/docs/flex-inference)。"Priority 推理的价格比标准 API 高 75%–100%,并按 token 计费"(ai.google.dev/gemini-api/docs/priority-inference)。Gemini API Contributor Tier 是仅限邀请的私有预览。符合条件的用户将通过电子邮件收到邀请。它为 Gemini 4 Argon 和 Gemini 4 Hydrogen 提供最高 50% 的 token 费用折扣。Google 使用这些模型的数据来改进其产品。"请勿提交敏感或个人信息"(ai.google.dev/gemini-api/docs/logs-policy)。Gemini 3.8 Live、Gemini 3.8 Live Extended Thinking 和 Gemini 3.1 Flash Live Preview 在免费层级支持使用 Google 搜索进行接地(Grounding)。Gemini 4 Hydrogen、Gemini 4 Argon 以及 Gemini 3.x Flash、Flash-Lite 和 Pro 模型在免费层级不支持该功能。在付费层级,每月 5,000 次搜索请求免费,在 Gemini 3 及更新型号之间共享,之后每 1,000 次收费 $14。2026-03-02 之后开设的账户无法将 $300 的 Google Cloud 欢迎额度用于 Gemini API。

我们于 2026-11-09 从 https://ai.google.dev/pricing 读到该内容,我们的核对记录为:该页面将 Google Gemini API 称为 "gemini api",并列出 "$2.00"、"$4.00"、"$10.00" 和 "$20.00"。

Gemini API 免费层级无需信用卡或结算账户;关联结算账户并预付款会将你转入付费层级。(来自 ai.google.dev/gemini-api/docs/billing,阅读于 2026-10-22。)

Google 的定价页面称,免费层级的内容会被用于改进 Google 的产品。(来自 ai.google.dev/gemini-api/docs/pricing,阅读于 2026-10-04。)

对于欧洲经济区、瑞士和英国以外的开发者,Google 的条款称人工审核人员可能会阅读免费层级的提示词和回复,Google 表示不要在免费层级发送敏感、机密或个人信息。(来自 ai.google.dev/gemini-api/terms,阅读于 2026-10-04。)

2026 年 10 月 26 日或之后创建的付费层级项目默认存储 Generate Content API 的请求和回复。在该日期之前创建的项目保留其现有的 Generate Content API 存储设置,该设置默认关闭,除非在 AI Studio 中开启。Interactions API 在所有项目中默认存储请求,包括 2026 年 10 月 26 日之前创建的项目。付费层级将存储的交互保留 55 天,免费层级保留 1 天。日志记录也涵盖通过 OpenAI 兼容端点发起的调用。日志最长保留 55 天,可配置为 7 天、14 天或 28 天。除非共享,日志不会用于改进 Google 的产品。在 AI Studio 中可针对每个 API 独立切换日志记录,请求中设置 store=false 会针对该请求关闭日志记录。(来自 ai.google.dev/gemini-api/docs/logs-policy,阅读于 2026-11-06。)

在 Interactions API 上设置 store=false 可阻止存储,且 inco

Google Gemini API Free Tier 2026: Gemini 4 Hydrogen and 3.8 Flash Available for Free

本文来源:https://agentdeals.dev/vendor/google-gemini-api
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。

Google Gemini API free tier includes Free tier: Gemini 4 Hydrogen, the only Gemini 4 model on the free tier, Gemini 3.8 Flash… Verified November 2026. Compare with 32 alternatives in AI / ML.

Subtypes in AI / ML: llm_api — the vendor runs language or multimodal models on its own infrastructure and sells calls to them by model name; you send a prompt and receive a completion; embeddings_api — returns a vector for text or media so it can be compared to other vectors; the vector is the output, not a completion; speech_api — converts recorded or streamed speech to text, or text to speech. We read that on 2026-09-01 from https://ai.google.dev/pricing , where it says: “Our 3.1 Flash Text-to-Speech audio model optimized for price-performant, low-latency, controllable speech generation.” How we use this .

Limits, pricing history, and 32 alternatives. Verified November 2026. Last updated 2026-11-21.

Google Gemini API's free tier offers Free tier: Gemini 4 Hydrogen, the only Gemini 4 model on the free tier, Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite… We rate it stable. None of the 21 recorded changes narrowed the terms. Best for ai / ml workloads — 32 alternatives available.

Free tier: Gemini 4 Hydrogen, the only Gemini 4 model on the free tier, Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, Gemini 3 Flash Preview, Gemini Embedding 2 and Gemma 4 are free of charge. Gemini 4 Carbon, Gemini 4 Argon and Gemini 4 Neon are paid only. Also free of charge are Gemini 3.8 Live (real-time voice), Gemini 3.5 Live Translate (translation), Gemini 3.5 Transcribe (speech-to-text), Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS (text-to-speech). Gemini Decision (gemini-decision-1), released 2026-11-11, is a multimodal decision model available through the Decisions API. It answers yes/no, choice and rubric questions with probabilities and generates zero output tokens, so it has no output price; input is free of charge on the free tier with 10,000 requests per day, and $0.10 per million input tokens on the paid tier. Gemini 4 Hydrogen (gemini-4-hydrogen), released 2026-11-12, is free of charge on the Gemini API free tier for input, output and context caching. On the paid tier, Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens (output includes thinking tokens), with context caching at $0.075 (implicit caching only); on the Batch API, Gemini 4 Hydrogen is $0.75 input and $3.75 output. The other Gemini 4 models, Gemini 4 Carbon (gemini-4-carbon), Gemini 4 Argon (gemini-4-argon) and Gemini 4 Neon (gemini-4-neon), are paid only, as are Gemini 3.1 Pro Preview and Gemini Omni 1.2 Flash (gemini-omni-1.2-flash). Gemini 4 Carbon, which Google calls its most capable reasoning model, has been generally available since 2026-11-10 and is not available on the Gemini API free tier. Gemini 4 Argon, generally available since 2026-10-13, is not available on the Gemini API free tier. Gemini 4 Neon (gemini-4-neon) has been generally available since 2026-11-18, is not available on the Gemini API free tier, and costs $3.00 per 1M input tokens and $15.00 per 1M output tokens on the paid tier, and $1.50 per 1M input tokens and $7.50 per 1M output tokens on the Batch API. According to ai.google.dev/gemini-api/docs/google-ai-plans, "Gemini 4 Argon is not available on the Free plan." Gemini 4 Argon is available through the Gemini API on the paid tier. "Direct use of the Gemini API (such as using API keys or external applications) is billed and managed separately," per ai.google.dev/gemini-api/docs/google-ai-plans. Google AI Pro and Ultra provide access to Gemini 4 Argon in Google AI Studio, per ai.google.dev/gemini-api/docs/google-ai-plans. Gemini 4 Argon is in Antigravity on Google AI Ultra and paid Google AI Pro. In Google AI Studio, Gemini 4 Carbon requires a Google AI Ultra plan and is not available on the Free or Google AI Pro plans (aistudio.google.com/docs/google-ai-plans). In Google AI Studio, Gemini 4 Neon is available on Google AI Pro and AI Ultra, not on the Free plan. In Antigravity, Gemini 4 Carbon is available on Google AI Ultra and Enterprise only (antigravity.google/docs/models). On a Google AI Pro trial, Argon is only available "on trial with eligible premium devices" (antigravity.google/docs/models). Claude Opus 5.5 and Claude Sonnet 5.5 are not included on Google AI Pro trials; trial users and those with memberships through third-party partners, Pixel Pass or Google Fi manage subscriptions through Google One. Google AI Pro via partner offers like Jio's does not include Gemini 4 Argon, Claude Sonnet 5.5 or Claude Opus 5.5 in Antigravity. Per a Google staff member on discuss.ai.google.dev (2026-10-21), "Those frontier models are restricted to directly billed (non-trial/non-promotional) Google AI Pro, Google AI Ultra and Enterprise plans." No Gemini image model has a free tier in the API. Nano Banana 2.1 (gemini-nano-banana-2.1) became generally available on 2026-10-06. It costs $0.0336 per 1K image, $0.0504 per 2K image and $0.113 per 4K image. The Batch API halves those prices. Nano Banana Pro costs $0.134 per 1K or 2K image and $0.24 per 4K image. Except for Gemini Decision, Google publishes no free-tier rate limits; each project's limits are shown in Google AI Studio. Developers report 429 errors showing 20 requests per day for Gemini 3.x Flash models and 500 requests per day for 3.x Flash-Lite models as of September 2026. Rate limits apply per project, not per API key. Daily request quotas reset at midnight Pacific time, per Google's rate-limits page. Since 2026-09-18 Google serves the Gemini 2.5 models only to users who have used them before, and points new projects to 3.5 Flash-Lite or 3.8 Flash. If your app calls gemini-3.7-flash, Google deprecated it on 2026-10-08. Requests to gemini-3.7-flash are routed automatically to gemini-3.8-flash. Google says to update the model string to gemini-3.8-flash. Existing users can call gemini-2.5-pro and gemini-2.5-flash until 2026-12-01, when Google shuts both down. From that date, requests to gemini-2.5-pro route to gemini-3.8-flash and are billed at its rates. Requests to gemini-2.5-flash route to gemini-3.5-flash-lite and are billed at its rates. Update your model string before 2026-12-01 and review Google’s migration guides for breaking API changes. gemini-2.5-flash-lite is not deprecated. If your app calls Gemini 3.5 Flash (gemini-3.5-flash), Google deprecated it on 2026-10-08. Requests to gemini-3.5-flash are routed automatically to gemini-3.6-flash. Google says to update the model string to gemini-3.6-flash or gemini-3.8-flash. Google shut down Gemini Omni Flash Preview (gemini-omni-flash-preview) on 2026-10-22. Google's replacement is gemini-omni-1.2-flash. Google shuts down Gemini Omni 1.1 Flash (gemini-omni-1.1-flash) on December 3, 2026; after that, requests that name gemini-omni-1.1-flash are answered by gemini-omni-1.2-flash at Gemini Omni 1.2 Flash rates. Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite) can be called until 2027-05-07, when Google shuts it down. Google's replacement is gemini-3.5-flash-lite. Paid, per million tokens (input/output; output prices include thinking tokens): Gemini 4 Carbon $2/$10 through 2026-11-30 (context caching $0.10, then $0.20, implicit caching only); Gemini 4 Argon $2/$10 through 2026-11-30 (context caching $0.10, then $0.20, implicit caching only); Gemini 3.8 Flash $0.75/$3.75 until 2026-12-31, then $1.50 input and $7.50 output from 2027-01-01 (3.6 Flash: the same prices and dates); Gemini 3.5 Flash-Lite (not gemini-3.5-flash) $0.30/$2.50; Gemini 3.1 Flash-Lite $0.25/$1.50; Gemini 3.1 Pro Preview $2/$12 (prompts up to 200K tokens; prompts over 200K tokens cost $4 input and $18 output). Through 2026-11-30, Gemini 4 Argon's Standard output price is below Gemini 3.1 Pro Preview's for prompts up to 200K tokens, with the same input price; from 2026-12-01 Argon's is higher. From December 1, 2026, Gemini 4 Argon will cost $4 per million input tokens and $20 per million output tokens for Standard, $2 input and $10 output for Batch API, $2 input and $10 output for Flex, and $7.20 input and $36 output for Priority. From December 1, 2026, Gemini 4 Carbon will also cost $4 per million input tokens and $20 per million output tokens for Standard, $2 input and $10 output for Batch API and Flex, and $7.20 input and $36 output for Priority. The Batch API costs half the standard price; Gemini 3.8 Flash is $0.375 input and $1.875 output per million tokens through 2026-12-31. Gemini 4 Carbon and Gemini 4 Argon on the Batch API are $1 input and $5 output through 2026-11-30. Google also sells two tiers, Flex and Priority, both in Preview. A request picks one with the service_tier field ("flex" or "priority"); without it the request is Standard. Gemini 4 Carbon and Gemini 4 Argon on Flex are $1 input and $5 output through 2026-11-30; on Priority they are $3.60 input and $18 output through 2026-11-30. "The Gemini Flex API is an inference tier that offers a 50% cost reduction compared to standard rates, in exchange for variable latency and best-effort availability" (ai.google.dev/gemini-api/docs/flex-inference). "Priority inference is priced at 75-100% more than the standard API and billed per token" (ai.google.dev/gemini-api/docs/priority-inference). The Gemini API Contributor Tier is an invite-only private preview. Eligible users will be invited by email. It offers up to 50% off token costs for Gemini 4 Argon and Gemini 4 Hydrogen. Google uses the data from those models to improve its products. "Please don't submit sensitive or personal information" (ai.google.dev/gemini-api/docs/logs-policy). Grounding with Google Search is supported on the free tier for Gemini 3.8 Live, Gemini 3.8 Live Extended Thinking and Gemini 3.1 Flash Live Preview. It is not available on the free tier for Gemini 4 Hydrogen, Gemini 4 Argon or the Gemini 3.x Flash, Flash-Lite and Pro models. On the paid tier, 5,000 search requests a month are free, shared across Gemini 3 and newer models, then $14 per 1,000. Accounts opened after 2026-03-02 cannot spend the $300 Google Cloud welcome credit on the Gemini API.

We read that on 2026-11-09 from https://ai.google.dev/pricing , and our check recorded: the page names Google Gemini API as "gemini api" and states "$2.00" and "$4.00" and "$10.00" and "$20.00" .

The Gemini API Free Tier needs no credit card or billing account; linking a billing account and prepaying moves you to the Paid Tier. (From ai.google.dev/gemini-api/docs/billing , read 2026-10-22.)

Google's pricing page says free-tier content is used to improve Google's products. (From ai.google.dev/gemini-api/docs/pricing , read 2026-10-04.)

For developers outside the European Economic Area, Switzerland and the United Kingdom, Google's terms say human reviewers may read free-tier prompts and responses, and Google says not to send sensitive, confidential or personal information on the free tier. (From ai.google.dev/gemini-api/terms , read 2026-10-04.)

Paid-tier projects created on or after October 26, 2026, store Generate Content API requests and responses by default. Projects created before that date keep their existing Generate Content API storage setting, which is off unless it was turned on in AI Studio. The Interactions API stores requests by default in all projects, including projects created before October 26, 2026. The Paid Tier keeps stored interactions for 55 days and the Free Tier for 1 day. Logging also covers calls made through OpenAI compatibility endpoints. Logs are retained for up to 55 days, configurable to 7, 14 or 28 days. Logs are not used to improve Google's products unless shared. Logging can be toggled independently for each API in AI Studio, and store=false on a request turns it off for that request. (From ai.google.dev/gemini-api/docs/logs-policy , read 2026-11-06.)

Setting store=false on the Interactions API prevents storage and is inco

暂无评论,快来发表第一条评论吧!No comments yet. Be the first!

📮 需求咨询📮 Inquiry