API 接入Gemini 3.6 Flash
数据驻留：未公开 · 隐私：未公开 · SLA：未公开来源：Gemini API and Google AI Studio available regions ↗选择要核对的信息，直接进入对应章节；各项事实均保留版本、条件和来源。
10/14 项有公开值 · 当前版本 Gemini 3.6 Flash · 数据截止 2026-10-22
页面只展示已审核 Claim；待审核数据不会被当作公开事实。只展示已审核事实；未公开、冲突和过期状态不会被补猜。
只判断选型资料是否足够，不评价模型能力高低。
所有必填事实均通过状态、来源、证据与时效校验。最早核验时间：2026-10-22。
release_datelifecycle_statuscapability_tagsdeployment_optionscontext_window_tokensapi_idinput_price_usd_per_mtokoutput_price_usd_per_mtokavailabilityGemini 3.6 Flash 是 Google DeepMind 的 Gemini 3 模型，年鉴当前记录 1 个版本，最新公开记录为 Gemini 3.6 Flash。
权重为未披露，代码为未披露，训练数据为未披露，部署方式为API 服务；这些维度分别判断，不能合并成单一“开源/闭源”结论。
当前公开快照的上下文窗口为 1.0M tokens，架构为 未公开；这里只使用通过审核且来源允许公开采集的 Claim。
5 个维度暂无可公开投影的审核记录
补充来源或线索会进入投稿队列，经编辑核验后才会成为公开事实。当前来源记录 4 个。
技术事实、业务价值、企业治理和证据质量分区呈现
厂商、家族、API ID、日期与生命周期
Dense/MoE、参数、层数、专家与 Tokenizer
预训练、SFT、偏好优化与安全对齐
教师/学生、基础模型、轨迹和限制
权重、代码、数据、许可证、部署与 API
API、托管云、地区、集成、隐私与 SLA
输入输出、缓存、Batch 与部署成本边界
数据、权限、审计、合规、安全与人工兜底
11 条已审核事实 · 全部来自公开来源闸门通过的记录
尚无已审核公开记录的维度：02 能力与任务、09 性能与评测、11 业务场景、12 落地与提效。查看资料缺口 ↑
关系只来自年鉴数据库中已登记的归属字段。
当前最新版本的 approved Claim 投影 · 23 条历史事实正在复核
接口兼容与业务适配均以来源绑定记录为准，不由模型名称或能力标签推断。
“兼容接口/平台”仅代表来源明确登记的接入边界，不等同于全部第三方工具都可直接使用。
下载、API、客户端和更新内容只展示已登记的来源事实；未登记不作推断。
230 个已登记地区 · 230 条版本级记录
保留发布日期精度、生命周期节点和原始来源，未公开日期不会被推断。
模型版本 · active
Google's deprecations table lists July 21, 2026 as the release date for gemini-3.6-flash.
来源：Gemini deprecations ↗显示最新核验的 8 条 · 共 11 条已审核事实
Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
Re-checked 2026-10-22: Google still lists the same 230 countries and territories for Gemini API and Google AI Studio, with no names added or removed since the 2026-08 capture.
1 个版本 · 每项可回到来源与技术解释
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the model page lists Model code gemini-3.6-flash as the stable version.
来源：Gemini 3.6 Flash model details ↗Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: Google's available-regions page lists the same 230 countries and territories for the Gemini API and Google AI Studio; the 230 approved country rows for this version remain the public projection.
来源：Gemini API and Google AI Studio available regions ↗Re-checked 2026-10-22: Google still lists the same 230 countries and territories for Gemini API and Google AI Studio, with no names added or removed since the 2026-08 capture.
引用文本与接口返回都只包含已审核公开事实
Google DeepMind Gemini 3.6 Flash｜最新版本 Gemini 3.6 Flash｜已审核事实 11 条｜公开来源 4 个｜数据截止 2026-10-22｜AI 年鉴｜https://ainianjian.com/models/model.google.gemini-3-6-flash
公开接口返回该模型的版本、已审核事实 11 条及其来源信息，可直接用于脚本或对比。
https://api.ainianjian.com/api/models/model.google.gemini-3-6-flash ↗curl -s 'https://api.ainianjian.com/api/models/model.google.gemini-3-6-flash'
技术规格使用当前版本已审核且来源允许公开采集的事实；模型级开放信息与跨版本地区记录分别标注范围。请按每项适用范围核对，未登记字段显示「未公开」，不使用估算值填充。
Re-checked 2026-10-22: Google still lists the same 230 countries and territories for Gemini API and Google AI Studio, with no names added or removed since the 2026-08 capture.
Google states that the Gemini API and Google AI Studio are available in listed countries and territories. This initial curated slice records the explicitly present United States, Canada, United Kingdom, Japan, Australia, and India entries for the Gemini API / Google AI Studio channel; it does not assert Vertex AI or third-party cloud availability.
Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
Gemini API deprecations page (re-checked 2026-10-22): the Gemini 3 table lists gemini-3.6-flash with release date July 21, 2026 and shutdown date 'No shutdown date announced'.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the model page lists code execution, computer use (preview), function calling and thinking for agentic use, and accepts video and audio input; the page does not describe a dedicated speech-to-text or text-to-speech product, so no audio-generation price is claimed.
Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22 on the Gemini 3.6 Flash model page: input token limit 1,048,576, output token limit 65,536.
来源：Gemini 3.6 Flash model details ↗Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the model page presents the stable gemini-3.6-flash endpoint and Google AI Studio try-it link; no Vertex AI, cloud-marketplace or self-hosted option is asserted here.
来源：Gemini 3.6 Flash model details ↗Gemini 3.6 Flash model page (re-checked 2026-10-22): Model code gemini-3.6-flash; inputs Text, Image, Video, Audio and PDF; output Text; input token limit 1,048,576; output token limit 65,536; supported capabilities include caching, code execution, computer use (preview), function calling, search grounding, structured outputs, thinking and URL context; the stable version is gemini-3.6-flash, latest update July 2026.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the pricing page states $1.50 per 1M input tokens starting January 1, 2027.
来源：Gemini API pricing ↗Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: standard paid-tier input price $0.75 per 1M tokens through December 31, 2026; the $1.50 price applies from January 1, 2027 and is recorded as a separate claim.
来源：Gemini API pricing ↗Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the deprecations table shows no shutdown date announced for gemini-3.6-flash; the pricing page calls it the previous-generation Flash model, not a retired one.
来源：Gemini deprecations ↗Gemini API deprecations page (re-checked 2026-10-22): the Gemini 3 table lists gemini-3.6-flash with release date July 21, 2026 and shutdown date 'No shutdown date announced'.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: the pricing page states $7.50 per 1M output tokens starting January 1, 2027.
来源：Gemini API pricing ↗Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22: standard paid-tier output price $3.75 per 1M tokens including thinking tokens through December 31, 2026; the $7.50 price applies from January 1, 2027 and is recorded as a separate claim.
来源：Gemini API pricing ↗Gemini API pricing page (re-checked 2026-10-22): Gemini 3.6 Flash standard paid tier is $0.75 per 1M input tokens and $3.75 per 1M output tokens (including thinking tokens) through December 31, 2026; the page states $1.50 input and $7.50 output starting January 1, 2027. Context caching is $0.075 per 1M tokens with $0.50 per 1M tokens per hour storage through the same date.
高置信度，已绑定来源与证据。
条件：Verified on 2026-10-22 on the Gemini API deprecations page; the Gemini 3 table lists gemini-3.6-flash released July 21, 2026.
来源：Gemini deprecations ↗Gemini API deprecations page (re-checked 2026-10-22): the Gemini 3 table lists gemini-3.6-flash with release date July 21, 2026 and shutdown date 'No shutdown date announced'.