{"id":"model.google.gemini-1-5-pro","name":"Gemini 1.5 Pro","family":"Gemini 1.5","type":"frontier","modalities":[],"capabilities":[],"openness":{"weights":null,"code":null,"data":null,"license":null,"deployment":null,"api":null},"keySpecs":{"contextWindowTokens":null,"extendedContextWindowTokens":null,"totalParameters":null,"activeParameters":null,"architectureType":null,"baseModel":null,"inputPriceUsdPerMtok":null,"outputPriceUsdPerMtok":null,"concurrencyLimitRequests":null},"organization":{"id":"org.google-deepmind","name":"Google DeepMind","websiteUrl":"https://deepmind.google"},"brand":{"id":"brand.google.gemini","name":"Gemini","websiteUrl":"https://ai.google.dev/gemini-api/docs/models"},"product":{"id":"product.google.gemini-api","name":"Gemini API","websiteUrl":"https://ai.google.dev/gemini-api/docs/models"},"origin":"international","versions":[{"id":"version.google.gemini-1-5-pro-001","name":"Gemini 1.5 Pro 001","externalModelId":"gemini-1.5-pro-001","kind":"snapshot","releaseDate":"2024-05-24","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"retired","knowledgeCutoff":null,"claims":[],"benchmarks":[]},{"id":"version.google.gemini-1-5-pro-002","name":"Gemini 1.5 Pro 002","externalModelId":"gemini-1.5-pro-002","kind":"snapshot","releaseDate":"2024-09-24","datePrecision":"day","publicAvailableAt":null,"lifecycleStatus":"retired","knowledgeCutoff":null,"claims":[],"benchmarks":[]},{"id":"version.google.gemini-1-5-pro","name":"Gemini 1.5 Pro","externalModelId":null,"kind":"semantic","releaseDate":null,"datePrecision":"unknown","publicAvailableAt":null,"lifecycleStatus":"unknown","knowledgeCutoff":null,"claims":[{"id":"claim.version.google.gemini-1-5-pro.7-eleven-internal-it-chatbot","fieldKey":"enterprise_use_case.internal_it_chatbot","value":{"value":"Internal IT issue resolution, employee onboarding and query responses"},"rawValue":"Internal IT chatbot for employees","ingestionOrigin":"curated_official","unit":null,"condition":"7-Eleven Vietnam public customer case; built with Vertex AI Agent Builder, Dialogflow CX and Gemini 1.5 Pro","status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-04 17:18:08.6982+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.google.customer.711-vietnam","title":"7-Eleven Vietnam: Easing IT workloads with a customized, AI-powered chatbot","url":"https://cloud.google.com/customers/711-vietnam","accessedAt":"2026-09-17 15:21:41.168+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:24.737+08"},"evidence":{"id":"evidence.google.customer.711-vietnam.2026-08","locator":"Public customer case: results, chatbot architecture, POC-to-production and 140-store sections","excerpt":"Google Cloud's public case explicitly names Gemini 1.5 Pro in 7-Eleven Vietnam's internal IT chatbot, built with Vertex AI Agent Builder and Dialogflow CX. It reports 50% less time spent fixing IT issues, support for employees across 140 stores, and POC/testing before production. The case does not publish a dated API model ID, issue sample, exact time baseline, cost, quality evaluation or independent validation."}},{"id":"claim.version.google.gemini-1-5-pro.gelato-ticket-triage","fieldKey":"enterprise_use_case.ticket_triage","value":{"value":"Engineering-support ticket triage and customer-support error categorization"},"rawValue":"Ticket triage and support error categorization","ingestionOrigin":"curated_official","unit":null,"condition":"Gelato public customer case; result is produced by Gemini with Vertex AI and surrounding support systems, so it is not an isolated model-only causal estimate","status":"approved","confidence":"high","reviewedBy":"system:curated_official","reviewedAt":"2026-08-04 17:18:08.6982+08","effectiveFrom":null,"effectiveTo":null,"source":{"id":"source.google.customer.gelato","title":"Gelato: Bringing efficient, high-quality local production to global ecommerce with Gemini","url":"https://cloud.google.com/customers/gelato","accessedAt":"2026-09-17 15:21:44.447+08","robotsStatus":"allowed","collectionEligibility":"eligible","collectionCheckedAt":"2026-09-17 15:17:24.742+08"},"evidence":{"id":"evidence.google.customer.gelato.2026-08","locator":"Public customer case: support-ticket triage, Gemini 1.5 Pro model selection and error categorization sections","excerpt":"Google Cloud's public case explicitly names Gemini 1.5 Pro for Gelato's engineering-support ticket triage and customer-support error categorization. It reports 120 hours of weekly manual tasks saved, ticket-assignment accuracy increasing from 60% to 90%, and Gemini automatically assigning tickets to the correct engineering team. The case also says Gelato planned to use Gemini 2.0 for future product-quality image recognition; that future plan is not attributed to Gemini 1.5 Pro."}}],"benchmarks":[]}],"dataUpdatedAt":"2026-08-04 17:18:08.6982+08","latestVersion":{"id":"version.google.gemini-1-5-pro-002","name":"Gemini 1.5 Pro 002","externalModelId":"gemini-1.5-pro-002","status":"retired"},"dataQuality":{"approved":2,"pending":0,"stale":8,"conflicted":0},"availabilityRegions":[],"availabilityChannels":[],"availabilityScopes":[],"decisionReadiness":{"overall":"incomplete","evaluatedAt":"2026-11-01T12:10:10.617Z","tracks":[{"key":"api","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]},{"key":"self_hosted","applicable":false,"grade":"incomplete","verifiedAt":null,"satisfiedFields":[],"missingFields":[],"missingEvidenceFields":[],"staleFields":[],"conflictedFields":[],"ineligibleSourceFields":[],"reasons":[],"fields":[]}]},"timeline":[{"id":"timeline.version.version.google.gemini-1-5-pro-001","kind":"version","subjectId":"version.google.gemini-1-5-pro-001","date":"2024-05-24","datePrecision":"day","title":"Gemini 1.5 Pro 001","summary":"模型版本 · retired","eventType":"version","lifecycleStatus":"retired","source":null},{"id":"event.version.google.gemini-1-5-pro-001.release-2024-05-24","kind":"event","subjectId":"version.google.gemini-1-5-pro-001","date":"2024-05-24","datePrecision":"day","title":"Gemini 1.5 Pro 001 released on Vertex AI","summary":"Google Cloud lists gemini-1.5-pro-001 release date as May 24, 2024 in the Gemini Enterprise Agent Platform lifecycle table.","eventType":"release","lifecycleStatus":null,"source":{"id":"source.google.vertex-ai.model-versions","title":"Model versions and lifecycle","url":"https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions"}},{"id":"timeline.version.version.google.gemini-1-5-pro-002","kind":"version","subjectId":"version.google.gemini-1-5-pro-002","date":"2024-09-24","datePrecision":"day","title":"Gemini 1.5 Pro 002","summary":"模型版本 · retired","eventType":"version","lifecycleStatus":"retired","source":null},{"id":"event.version.google.gemini-1-5-pro-002.release-2024-09-24","kind":"event","subjectId":"version.google.gemini-1-5-pro-002","date":"2024-09-24","datePrecision":"day","title":"Gemini 1.5 Pro 002 released on Vertex AI","summary":"Google Cloud lists gemini-1.5-pro-002 release date as September 24, 2024 in the Gemini Enterprise Agent Platform lifecycle table.","eventType":"release","lifecycleStatus":null,"source":{"id":"source.google.vertex-ai.model-versions","title":"Model versions and lifecycle","url":"https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions"}},{"id":"event.version.google.gemini-1-5-pro-001.retired-2025-05-24","kind":"event","subjectId":"version.google.gemini-1-5-pro-001","date":"2025-05-24","datePrecision":"day","title":"Gemini 1.5 Pro 001 retired on Vertex AI","summary":"Google Cloud lists May 24, 2025 as the retirement date and gemini-2.5-flash as the recommended upgrade. The statement is scoped to the cited Gemini Enterprise Agent Platform lifecycle table.","eventType":"deprecation","lifecycleStatus":null,"source":{"id":"source.google.vertex-ai.model-versions","title":"Model versions and lifecycle","url":"https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions"}},{"id":"event.version.google.gemini-1-5-pro-002.retired-2025-09-24","kind":"event","subjectId":"version.google.gemini-1-5-pro-002","date":"2025-09-24","datePrecision":"day","title":"Gemini 1.5 Pro 002 retired on Vertex AI","summary":"Google Cloud lists September 24, 2025 as the retirement date and gemini-2.5-flash as the recommended upgrade. The statement is scoped to the cited Gemini Enterprise Agent Platform lifecycle table.","eventType":"deprecation","lifecycleStatus":null,"source":{"id":"source.google.vertex-ai.model-versions","title":"Model versions and lifecycle","url":"https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions"}},{"id":"timeline.version.version.google.gemini-1-5-pro","kind":"version","subjectId":"version.google.gemini-1-5-pro","date":null,"datePrecision":"unknown","title":"Gemini 1.5 Pro","summary":"模型版本 · unknown","eventType":"version","lifecycleStatus":"unknown","source":null}],"availability":[],"enterpriseCases":[{"id":"enterprise-case.google.711-vietnam","organizationName":"7-Eleven Vietnam","industry":"retail","useCase":{"id":"usecase.enterprise.knowledge-base","title":"企业知识库问答"},"deploymentStage":"production","evidenceLevel":"C","caseUrl":"https://cloud.google.com/customers/711-vietnam","publishedAt":null,"baselineSummary":"The case says a previous third-party chatbot struggled with industry-specific and complex questions, and that printer issues previously required an IT engineer to be on call; exact time, volume and quality baselines are not published.","resultSummary":"Google Cloud's public case names Gemini 1.5 Pro in 7-Eleven Vietnam's internal IT chatbot, built with Vertex AI Agent Builder and Dialogflow CX. The chatbot supports employees across 140 stores, resolves printer and other IT questions with structured flows and documentation, and the case reports 50% less time spent fixing IT issues. The team completed proof-of-concept and testing before production.","limitations":"Vendor-authored Google Cloud case and partner-supported implementation; the 50% time reduction is not isolated from Agent Builder, Dialogflow CX, conversation design, documentation and human escalation. The page does not publish a dated API model ID, issue sample, exact baseline, cost, quality/error rate, measurement period or independent validation.","source":{"id":"source.google.customer.711-vietnam","title":"7-Eleven Vietnam: Easing IT workloads with a customized, AI-powered chatbot","url":"https://cloud.google.com/customers/711-vietnam"},"impactMetrics":[{"id":"impact-metric.google.711-vietnam.store-coverage","metricType":"experience","metricName":"Stores served by internal chatbot","baselineValueNumeric":null,"outcomeValueNumeric":140,"unit":"stores","deltaPercent":null,"measurementPeriod":"Current production coverage described on public customer case","measurementMethod":"Official Google Cloud customer case says the chatbot serves employees from 140 stores; active-user volume, query volume and service quality are not disclosed.","calculationStatus":"reported","calculationFormula":null,"sampleSize":null,"confidenceNote":null},{"id":"impact-metric.google.711-vietnam.it-time-reduction","metricType":"time","metricName":"IT issue-fixing time reduction","baselineValueNumeric":null,"outcomeValueNumeric":50,"unit":"percent reduction, vendor-reported","deltaPercent":null,"measurementPeriod":"Current state described on public customer case; exact period not disclosed","measurementMethod":"Official Google Cloud customer case reports 50% less time spent fixing IT issues; baseline duration, issue sample, measurement harness and independent validation are not disclosed.","calculationStatus":"reported","calculationFormula":null,"sampleSize":null,"confidenceNote":null}],"roiAssessments":[]},{"id":"enterprise-case.google.gelato","organizationName":"Gelato","industry":"technology and software","useCase":{"id":"usecase.customer-service.agent-assist","title":"客服坐席辅助"},"deploymentStage":"unknown","evidenceLevel":"C","caseUrl":"https://cloud.google.com/customers/gelato","publishedAt":null,"baselineSummary":"Gelato says the previous ticket-triage process took over 100 hours weekly and assigned only 60% of tickets correctly; the case does not publish a controlled study design, sample definition or measurement period.","resultSummary":"Google Cloud's public case names Gemini 1.5 Pro in Gelato's engineering-support ticket triage and customer-support error categorization. It reports 120 hours of weekly manual tasks saved and ticket-assignment accuracy increasing from 60% to 90%; Gemini automatically assigns tickets to the responsible engineering team. Gelato also describes instant error classification in customer-support systems.","limitations":"Vendor-authored Google Cloud case; the reported 120 hours, accuracy figures and support-system result are not isolated from Vertex AI, data preparation, workflow integration or human review. The page does not publish a dated API model ID, sample, evaluation method, measurement period, cost, quality beyond assignment accuracy or independent validation. The separate plan to use Gemini 2.0 for image-based product quality is not bound to this Gemini 1.5 Pro case.","source":{"id":"source.google.customer.gelato","title":"Gelato: Bringing efficient, high-quality local production to global ecommerce with Gemini","url":"https://cloud.google.com/customers/gelato"},"impactMetrics":[{"id":"impact-metric.google.gelato.ticket-assignment-accuracy","metricType":"quality","metricName":"Correct ticket assignment accuracy","baselineValueNumeric":60,"outcomeValueNumeric":90,"unit":"percent","deltaPercent":null,"measurementPeriod":"Before/after values described on public customer case; exact period not disclosed","measurementMethod":"Official Google Cloud customer case reports accuracy increasing from 60% to 90%; ticket sample, label policy, evaluation protocol and independent validation are not disclosed. No derived delta is stored.","calculationStatus":"reported","calculationFormula":null,"sampleSize":null,"confidenceNote":null},{"id":"impact-metric.google.gelato.ticket-triage-hours","metricType":"time","metricName":"Manual ticket-triage labor saved","baselineValueNumeric":null,"outcomeValueNumeric":120,"unit":"hours per week","deltaPercent":null,"measurementPeriod":"Current state described on public customer case; exact period not disclosed","measurementMethod":"Official Google Cloud customer case reports 120 hours of weekly labor saved; staffing denominator, sampling, human-review effort and independent validation are not disclosed.","calculationStatus":"reported","calculationFormula":null,"sampleSize":null,"confidenceNote":null}],"roiAssessments":[]}],"useCases":[{"id":"model-use-case.google.gelato","useCase":{"id":"usecase.customer-service.agent-assist","updatedAt":"2026-08-03 07:00:11.278772+08","industry":"cross-industry","functionGroup":"customer-service","workflowName":"support-operations","taskName":"工单总结、分类、回复建议与坐席辅助","title":"客服坐席辅助","description":"对话摘要、知识检索、回复建议、质检和工单分类。","maturityStage":"discovery","inputDescription":"客户对话、工单、知识库和服务政策","outputDescription":"分类、摘要、建议回复和升级判断","capabilityRequirements":["tool_calls","structured_output","long_context"],"humanInvolvement":"高风险、低置信度和投诉场景由人工坐席确认或接管。","prerequisites":"可检索知识库、权限隔离、质量抽检和人工升级路径。","constraints":"不得在缺少基线、样本和测量周期时推导自动化率或 ROI。"},"version":{"id":"version.google.gemini-1-5-pro","name":"Gemini 1.5 Pro"},"suitability":"conditional","humanInvolvement":"高风险、低置信度和投诉场景由人工坐席确认或接管。","prerequisites":"可检索知识库、权限隔离、质量抽检和人工升级路径。","constraints":"不得在缺少基线、样本和测量周期时推导自动化率或 ROI。","evidenceStatus":"observed_use","notes":"该关联表示公开案例中观察到的使用，不代表通用推荐或独立效果评估。","source":{"id":"source.google.customer.gelato","title":"Gelato: Bringing efficient, high-quality local production to global ecommerce with Gemini","url":"https://cloud.google.com/customers/gelato"}},{"id":"model-use-case.google.711-vietnam","useCase":{"id":"usecase.enterprise.knowledge-base","updatedAt":"2026-08-03 07:00:11.278772+08","industry":"cross-industry","functionGroup":"knowledge-management","workflowName":"enterprise-search","taskName":"企业文档检索、问答与引用回溯","title":"企业知识库问答","description":"基于企业文档、制度和知识库的检索增强问答。","maturityStage":"discovery","inputDescription":"企业文档、知识库索引、权限和用户问题","outputDescription":"带引用的答案、摘要和未命中说明","capabilityRequirements":["long_context","structured_output","tool_calls"],"humanInvolvement":"知识管理员维护资料与权限，关键答案由业务人员复核。","prerequisites":"可追溯文档库、访问控制、检索评测集和更新机制。","constraints":"模型未检索到证据时必须表达未知，不能补造企业事实。"},"version":{"id":"version.google.gemini-1-5-pro","name":"Gemini 1.5 Pro"},"suitability":"conditional","humanInvolvement":"知识管理员维护资料与权限，关键答案由业务人员复核。","prerequisites":"可追溯文档库、访问控制、检索评测集和更新机制。","constraints":"模型未检索到证据时必须表达未知，不能补造企业事实。","evidenceStatus":"observed_use","notes":"该关联表示公开案例中观察到的使用，不代表通用推荐或独立效果评估。","source":{"id":"source.google.customer.711-vietnam","title":"7-Eleven Vietnam: Easing IT workloads with a customized, AI-powered chatbot","url":"https://cloud.google.com/customers/711-vietnam"}}],"deploymentProfiles":[],"learningResources":[],"trainingProfiles":[],"publication":{"approvedClaimsOnly":true,"note":"页面只展示已审核 Claim；待审核数据不会被当作公开事实。"}}