---
格式版本: 2
标题: "Import DeepSeek V4 Flash 0731 into OCI Generative AI"
原文链接: "https://docs.oracle.com/en-us/iaas/releasenotes/generative-ai/deepseek-v4-flash-0731.htm"
发布日期: "2026-08-19"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:scrape:strict_html_body"
发布时间证据: "span class=vl-relnotedate: August 19, 2026"
发布时间校准原因: "正文中明确标注发布时间为2026年8月19日，且该日期紧邻标题，符合文章发布时间判定优先级。"
发布时间校准置信度: "1"
发布时间候选数量: 16
发布时间严格候选数量: 5
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-21T09:58:26+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 3
发布时间仲裁耗时毫秒: 20378
发现时间: "2026-08-21T09:56:49+08:00"
入库时间: "2026-08-21T01:58:46.426Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://docs.oracle.com/en-us/iaas/releasenotes"
匹配关键词:
  - "AI"
  - "deployment"
相关厂家:
  - "Oracle"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 28
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容为OCI模型导入说明，仅提及GPU集群形状，未涉及超节点/AI Rack架构、供电散热或互连等主题，与项目关注范围无关。"
AI质检模型: "tx-deepseek-v4-flash"
AI质检时间: "2026-08-21T09:59:21+08:00"
AI主题相关性: 3
AI来源权威性: 12
AI新颖性: 4
AI技术细节: 2
AI商业部署信号: 2
AI完整性: 5
AI摘要: "Oracle 在 OCI Generative AI 中新增支持导入 DeepSeek-V4-Flash-0731 模型，可创建端点并使用。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T02:13:14.385Z"
采集批次: "2026年8月21日9点50分40秒"
采集批次ID: "20260821-095040-035"
去重键: "https://docs.oracle.com/en-us/iaas/releasenotes/generative-ai/deepseek-v4-flash-0731.htm"
---

You can now import the [deepseek-ai/DeepSeek-V4-Flash-0731](https://docs.oracle.com/iaas/Content/generative-ai/imported-deepseek-models.htm) model into OCI Generative AI, create endpoints for it, and use it in the Generative AI service.

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash and supersedes the preview version with enhanced agentic capabilities. The model includes a speculative decoding module and supports low, high, and max reasoning-effort levels for agentic coding, tool use, and complex reasoning tasks.

In OCI Generative AI, use the following details for this model:

- **Model capability:** `TEXT_TO_TEXT`
- **Minimum dedicated AI cluster unit shapes:** `H100_X4`, `H200_X4`, `B200_X2`, and `B300_X2`

For the complete list of models that you can import, see [Models for Import](https://docs.oracle.com/iaas/Content/generative-ai/imported-models.htm). For available hardware and deployment steps, see [Managing Imported Models](https://docs.oracle.com/iaas/Content/generative-ai/manage-imported-models.htm#imported-models).